triage-validation
Skill1 starsChanged 3 months agoMITView on GitHub
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally-valid chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.
13 other projects use a version of this, 10 of them edited.
Adopted by
Most recently taken up by
- murrtada/bug-bounty-agent-skillsedited, first seen Nov 15, 2026
- SubhiSec/claude-ai-cyber-security-skillstheir own version, first seen Oct 25, 2026
- shuvonsec/claude-bug-bountyedited, first seen Oct 8, 2026
- Gabson0x/bountyforgeedited, first seen Sep 16, 2026
- ajtazer/heckitedited, first seen Sep 11, 2026
- conjure-3301/skillsedited, first seen Aug 17, 2026
Used with
Projects with it also use bugcrowd-reporting, bb-methodology and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
hhjkjkjkSkillbugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints, debug-info framing, user-enumeration with sensitive PII, theoretical-issue counter), chained-finding cross-reference patterns, target selection for QA-vs-prod programs, researcher-side hygiene (Bugcrowdninja email alias, account state restoration, friendly-tester posture). Use when filing a Bugcrowd submission, when VRT default seems wrong, when triager closes as OOS or downgrades severity, when chaining linked submissions, or when scope distinguishes production from QA. Pairs with report-writing and triage-validation.
Also in 8 projects that use this
hhjkjkjkSkillbb-methodology
Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator that combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on current hunting phase. Also use when asking "what should I do next" or "where am I in the process.
Also in 7 projects that use this
shuvonsecSkillagentic-app-audit
Black-box security audit of a DEPLOYED AI agent (not the MCP server behind it) — tool-call hijacking, cross-session memory poisoning, confused-deputy via connected tools, agent-to-agent IDOR, excessive agency / unconfirmed destructive actions, and privilege compromise where the agent holds broader perms than the user. Use when the target is a live assistant/agent product with tool access (bookings, email, payments, file/RAG, browsing) rather than a raw LLM chat box or an MCP server you can read.
Also in 3 projects that use this
shuvonsecSkillbug-chaining
Standalone bug chaining skill — synthesized from omni-killchain, omni-references/chaining-impact, triage-validation, apex-hunter, web2-vuln-classes, bug-bounty, and bb-methodology. Covers the complete chaining mindset: 10-question filter, 15 proven chain patterns (A–O) with payout data, escalation ladders per vuln class, conditional-chain table (when a standalone bug needs a gadget), impact-writing rules, CVSS chain multipliers, and 30-minute chain-or-move decision clock. Use when you have a low/medium finding and want to know how to chain it to Critical, or when strategizing what to hunt for maximum payout. Authorized testing only — bug bounty in-scope, pentest engagement, or CTF.
Also in 3 projects that use this
- +5 more from shuvonsec
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 10
- elementalsouls/Claude-BugHunter★ 6.1k22% same
- shuvonsec/claude-bug-bounty★ 5.9k43% same
- awarexone/Agentic-Bug-Hunter★ 5.9k43% same
- Awarexone/Agentic-Bug-Hunter★ 5.9k43% same
- Gabson0x/bountyforge★ 43134% same
- murrtada/bug-bounty-agent-skills★ 722% same
- Mikacr1138/claude-bug-bounty★ 348% same
- ajtazer/heckit★ 222% same
- conjure-3301/skills★ 048% same
- hhjkjkjk/Claude-skills★ 023% same
Wrote their own version · 3
- SubhiSec/claude-ai-cyber-security-skills★ 45same name
- 0xGhostCAT/claude-ai-cyber-security-skills★ 41same name
- ivRodriguezCA/MobHunt★ 37same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository50 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- agent-safetySkill
- ai-llmSkill
- apiSkill
- asset-graphSkill
- authSkill
- auto-researchSkill
- binary-analysisSkill
- business-logicSkill
- campaignSkill
- cicd-securitySkill
- cloudSkill
- cors-csrfSkill
- coverageSkill
- cross-accountSkill
- domain-modelSkill
- enrichmentSkill
- evaluation-harnessSkill
- file-uploadSkill
- graphql-auditSkill
- http-protocolSkill
- identity-domainSkill
- impact-verifierSkill
- meme-coin-auditSkill
- mobileSkill
- modern-browserSkill
- nuclei-scannerSkill
- oob-infraSkill
- osintSkill
- personaSkill
- plannerSkill
- privescSkill
- program-memorySkill
- race-conditionSkill
- rceSkill
- reconSkill
- reportingSkill
- sastSkill
- scope-managerSkill
- skill-scientistSkill
- sqliSkill
- ssrfSkill
- standard-catalogSkill
- technique-kbSkill
- traffic-corpusSkill
- vuln-intelSkill
- web3-auditSkill
- xssSkill
The file
We split this skill into the rules it gives an agent
8 rules. 3 are common, 4 are distinctive, and 1 is very specific to this project.
3
Common
Most of the 13 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 30
Ask IN ORDER. One wrong answer = STOP immediately.
- Common: line 78
Check the NEVER SUBMIT list below.
- Distinctive: line 90
IDOR / BOLA: must work with session A reading session B's data — if it only works with no auth, that's "missing auth" not IDOR (different …
- Distinctive: line 92
Priv-esc: must work with low-priv session reading high-priv data — if both sessions can already see it, no bug.
- Distinctive: line 94
Auth bypass: must work *without* a valid session — if it stops working when you log out, you've found a permissions issue, not a bypass.
- Distinctive: line 96
If you cannot answer the identity questions, treat the finding as unproven.
- Common: line 101
Run in sequence. ALL 4 must PASS.
- Very specific: line 187
Never-submit source list: scripts/never_submit_check.py + runbook runbooks/04-never-submit.md
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TRIAGE & VALIDATION
Overview
One wrong answer = STOP. Kill it. Move on.
"N/A hurts your validity ratio. Informative is neutral. Only submit what passes all 7 questions."
This skill is a pre-report quality gate. Run it on every candidate finding before spending time on a report: the 7-Question Gate disqualifies weak leads in minutes, the 4 pre-submission gates catch everything else, and the never-submit list stops known-invalid bug classes from ever reaching a report. The conditionally-valid table tells you which findings are only reportable with a proven chain.
- Workflow
run-gatewalks the 7-Question Gate and the 4 pre-submission gates. - Workflow
check-never-submitmatches a finding description against the always-rejected list and the common N/A kill signals. - Script
scripts/chain_validity.pychecks a candidate finding against the conditionally-valid chain-required table.
Quick Reference
The 7-Question Gate
Ask IN ORDER. One wrong answer = STOP immediately.
Q1: Can an attacker use this RIGHT NOW, step by step? Complete this template:
1. Setup: I need [own account / another user's ID / no account]
2. Request: [exact HTTP method, URL, headers, body — copy-paste ready]
3. Result: I can [read / modify / delete] [exact data shown in response]
4. Impact: The real-world consequence is [account takeover / PII read / money stolen]
5. Cost: Time: [X minutes], Capital: [$0 / $X subscription required]If you CANNOT write step 2 as a real HTTP request → KILL IT.
Q2: Is the impact on the program's accepted impact list? Go to the program page. Find "Vulnerability Types" or "Out of Scope."
- Critical: Any-user ATO without interaction, RCE, SQLi with data exfil, admin auth bypass
- High: Mass PII exfil, privilege escalation, internal SSRF with data, stored XSS all users
- Medium: IDOR on specific user non-critical data, XSS on sensitive page requiring click
- Low: Non-sensitive info disclosure, clickjacking with PoC If your bug maps to a listed exclusion → KILL IT.
Q3: Is the root cause in an in-scope asset?
- Vulnerable domain is on the in-scope list (not
*.internal.target.com) - It's a production asset (not staging/dev unless explicitly in scope)
- It's not a third-party service the company just uses (Stripe, Salesforce, Google Auth) If out-of-scope → KILL IT.
Q4: Does it require privileged access that an attacker can't realistically get?
- "Admin can do X" = centralization risk = KILL IT (on 99% of programs)
- "Non-admin can do X that only admin should do" = valid
- "Requires physical access / MFA device" = usually invalid
- "Requires compromised victim account to work" = questionable, low severity at best
Q5: Is this already known or accepted behavior?
- Program's disclosed reports: Ctrl+F endpoint name + bug class
- GitHub issues on target repo:
is:issue label:security ENDPOINT_NAME - Changelog — does it mention this behavior?
- API docs / design docs — is it documented as intended? If acknowledged/design decision → KILL IT.
Q6: Can you prove impact beyond "technically possible"?
- XSS → show actual cookie theft or session hijack, not just
alert(1) - SSRF → hit an internal endpoint that returns data, not just DNS ping
- SQLi → show actual data exfil from a real table, not just error message
- IDOR → show actual other-user's data in response, not just a 200 status code If you can only show "technically possible" → DOWNGRADE severity, not kill.
Q7: Is this a known-invalid bug class? Check the NEVER SUBMIT list below. If it's on this list without a chain → KILL IT.
Q8: Identity check — which session found this, and does it survive?
For any finding made under an authenticated hunt, record the answer to each:
1. Session ID: [12-char BBHUNT_SESSION_ID hash from audit.jsonl]
2. Identity: [low-priv user A / high-priv user B / API key / etc.]
3. Anonymous repro: Does the same request work with NO auth header?
4. Cross-identity: Does it work under session B with the same data scope?
5. Stale-cred repro: Does a logged-out / expired session still get the data?- IDOR / BOLA: must work with session A reading session B's data — if it only works with no auth, that's "missing auth" not IDOR (different bug, different severity).
- Priv-esc: must work with low-priv session reading high-priv data — if both sessions can already see it, no bug.
- Auth bypass: must work without a valid session — if it stops working when you log out, you've found a permissions issue, not a bypass.
- If you cannot answer the identity questions, treat the finding as unproven. Blank answers auto-fail on auth-related findings.
4 Pre-Submission Gates
Run in sequence. ALL 4 must PASS.
Gate 0: Reality Check (30 seconds)
[ ] Bug is REAL — confirmed with actual HTTP requests, not code reading alone
[ ] Bug is IN SCOPE — checked program scope page explicitly
[ ] Reproducible from scratch — can reproduce starting from fresh session
[ ] Evidence ready — screenshot, response body, or videoGate 1: Impact Validation (2 minutes)
[ ] Can answer: "What can attacker DO that they couldn't before?"
[ ] Answer is more than "see non-sensitive data" (unless program pays for info disclosure)
[ ] Real victim: another user's data, company's data, financial loss
[ ] Not relying on victim doing something unlikelyGate 2: Deduplication Check (5 minutes)
[ ] Searched HackerOne Hacktivity for this program + similar bug title/endpoint
[ ] Searched GitHub issues for target repo
[ ] Read most recent 5 disclosed reports for this program
[ ] Not a "known issue" in their changelog or public docs
[ ] Google: "TARGET_NAME ENDPOINT_NAME bug bounty"Gate 3: Report Quality (10 minutes)
[ ] Title: [Bug Class] in [Endpoint] allows [actor] to [impact]
[ ] Steps to Reproduce: copy-pasteable HTTP request
[ ] Evidence: screenshot/video of actual impact (not just 200 status)
[ ] Severity: matches CVSS 3.1 score AND program's severity definitions
[ ] Remediation: 1-2 sentences of concrete fix
[ ] NEVER used "could potentially" or "may allow"Workflow Selection
| Situation | Workflow |
| New candidate finding before any report work | run-gate |
| Finding description drafted, check against always-rejected list | check-never-submit |
| Finding matches a "chain required" class | check-never-submit output + scripts/chain_validity.py |
| All gates passed, time to write the report | hand off to reporting skill |
Available Workflows
run-gate
Runs the 7-Question Gate and the 4 pre-submission gates against a finding
directory (FINDING_DIR must contain at least description.txt and ideally
request.txt / response.txt). Writes a gate result markdown report.
Command (via bin/bb-run triage-validation run-gate):
mkdir -p $OUTDIR/triage && \
python3 .claude/skills/triage-validation/scripts/triage_gate.py --finding-dir "${FINDING_DIR:?Set FINDING_DIR}" --output $OUTDIR/triage/gate_result.mdOutputs: $OUTDIR/triage/gate_result.md. Safety tier: passive.
check-never-submit
Matches the finding description and evidence filenames against the NEVER SUBMIT list and the common N/A kill signals, and prints which rules the finding violates (each hit = kill the finding or build the required chain).
Command (via bin/bb-run triage-validation check-never-submit):
mkdir -p $OUTDIR/triage && \
python3 .claude/skills/triage-validation/scripts/never_submit_check.py --finding-dir "${FINDING_DIR:?Set FINDING_DIR}" --output $OUTDIR/triage/never_submit.mdOutputs: $OUTDIR/triage/never_submit.md. Safety tier: passive.
Evidence Required
| Artifact | File |
| Raw HTTP request used to reproduce | evidence/<finding>/request.txt |
| Response showing impact | evidence/<finding>/response.txt |
| Identity/session answers (auth findings) | gate result markdown |
| Chain PoC (conditionally-valid classes) | evidence/<finding>/poc.sh |
| Gate result + never-submit verdict | $OUTDIR/triage/*.md |
References
- Full rules:
references/shuvonsec-rules/hunting.mdandreferences/shuvonsec-rules/reporting.md - CVSS 3.1 scoring workflow:
reportingskill (cvss-score) - Never-submit source list:
scripts/never_submit_check.py+ runbookrunbooks/04-never-submit.md - Conditionally-valid chain table:
scripts/chain_validity.py - Redaction policy: gate reports may quote requests with cookies/tokens —
keep them local-only under
$OUTDIRand redact before committing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

