agentic-security-review
Skill0 starsChanged 6 months agoMITView on GitHub
Run the OWASP-aligned agentic security review path — covers goal hijacking, tool misuse, excessive agency, memory poisoning, secrets exposure, handoff failures, and observability. Opt-in from Stage 9 (Review) or the QA track. Not a new track — no state file or slash command namespace. Triggers "agentic security review", "agent security", "security review for agents", "/agentic-security-review".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- browoz/agentic-sdlc-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- browoz/agentic-sdlc-skills★ 4same 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- plugin-v2/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- plugin-v2/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agents.mdcCursor rule
- arc42-baselineSkill
- caveman-commitSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- create-goalSkill
- design-twiceSkill
- discovery-sprintSkill
- domain-contextSkill
- github-project-setupSkill
- grillSkill
- improve-codebase-architectureSkill
- issue-breakdownSkill
- issue-draftSkill
- issue-pr-syncSkill
- new-adrSkill
- new-glossary-entrySkill
- orchestrateSkill
- portfolio-trackSkill
- product-pageSkill
- project-reviewSkill
- project-runSkill
- project-scaffoldingSkill
- quality-assuranceSkill
- quality-metricsSkill
- record-decisionSkill
- review-fixSkill
- roadmap-managementSkill
- sales-cycleSkill
- specorator-designSkill
- specorator-improvementSkill
- specorator-onboardSkill
- stock-takingSkill
- tackle-issueSkill
- tdd-cycleSkill
- token-budget-reviewSkill
- tracer-bulletSkill
- ubiquitous-languageSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Locate the review doc: Read docs/agentic-security-review.md — it contains the 7 risk categories and checklists.
- Distinctive: line 63
Do not claim the system is "secure" or "certified" — use "risk-reduced" or "reviewed for known categories."
- Distinctive: line 64
Do not skip the finding record — undocumented risks have no mitigation trail.
- Distinctive: line 65
Do not create a new track namespace, state file, or slash command — this is an opt-in skill, not a track.
- Very specific: line 66
Do not modify docs/agentic-security-review.md during a review — findings go in the finding record, not the review doc.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agentic Security Review
An opt-in review path for identifying and mitigating risks unique to autonomous, tool-using agents. Invoke from Stage 9 (Review) or the Quality Assurance Track.
Scope: internal risk reduction. Not a certification or complete security guarantee.
When to use
- Feature adds or changes agent tool use.
- Stage 9 (Review) for agent-facing workflows.
- QA track scope includes agentic automation.
- Post-incident or near-miss involving autonomous agent behavior.
Procedure
- Locate the review doc. Read
docs/agentic-security-review.md— it contains the 7 risk categories and checklists. - Set up a finding record. Copy
templates/agentic-security-findings.mdtoquality/<review-slug>/agentic-security-findings.md. If no QA review is active, create a minimalquality/<feature-slug>/folder. - Work through each risk category. For every checklist item in
docs/agentic-security-review.md(read-only reference — do not edit the canonical doc):- Mark
[x]in the findings record if satisfied with evidence. - Mark open finding in the findings record if not satisfied.
- Skip with
not-applicable+ rationale in the findings record if the category doesn't apply.
- Mark
- Assess severity. For each open finding:
- critical — exploitable, high-impact, blocks release.
- high — exploitable or likely, requires mitigation before release.
- medium — possible exposure, mitigate in next sprint.
- low — theoretical, accepted or deferred with rationale.
- Record mitigations and residual risk. Fill in the finding-record fields: evidence, mitigation, residual risk, follow-up.
- Write verdict. Complete the Summary and Verdict sections of the finding record.
- Link from the review artifact. In Stage 9's
review.mdor the QAquality-review.md, add a section:## Agentic security review - Finding record: `quality/<slug>/agentic-security-findings.md` - Verdict: <complete / incomplete> - Blocker findings: <list or "none">
Reporting
On completion, report:
Agentic security review complete.
Finding record: quality/<slug>/agentic-security-findings.md
Categories reviewed: 7
Open findings: N (critical: X, high: Y, medium: Z, low: W)
Blocker findings: <list or "none">
Verdict: <complete / incomplete>Do not
- Do not claim the system is "secure" or "certified" — use "risk-reduced" or "reviewed for known categories."
- Do not skip the finding record — undocumented risks have no mitigation trail.
- Do not create a new track namespace, state file, or slash command — this is an opt-in skill, not a track.
- Do not modify
docs/agentic-security-review.mdduring a review — findings go in the finding record, not the review doc.
References
docs/agentic-security-review.md— full risk categories and checkliststemplates/agentic-security-findings.md— finding record templatedocs/quality-assurance-track.md— ISO 9001-aligned QA workflowmemory/constitution.md— Article IX (Reversibility)
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.

