threat-model
Skill4 starsChanged todayMITView on GitHub
[oh-my-agy] Structured security threat modeling workflow producing trust-boundary data-flow diagrams, STRIDE and OWASP Agentic/LLM risk enumeration, likelihood-impact scoring, file:line mitigations, and MCP/supply-chain audits. Use for $threat-model or when mapping attack surfaces, reviewing auth/agent/MCP architectures, or documenting security controls.
- Reads credentials
58 other projects use a version of this.
Adopted by
Most recently taken up by
- mgkvibez/sentinel-skillstheir own version, first seen Nov 8, 2026
- requie/endostacktheir own version, first seen Nov 8, 2026
- pat-lewczuk/skillstheir own version, first seen Nov 1, 2026
- Codeminer42/skillstheir own version, first seen Nov 1, 2026
- jmanico/grim-promptertheir own version, first seen Nov 1, 2026
- Q00/ouroborostheir own version, first seen Oct 25, 2026
Used with
Projects with it also use vuln-scan, supply-chain-review and 10 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.
AnthropicSkillvuln-scan
Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to "scan for vulns", "review this code for security issues", "find bugs in <dir>", or as the step between /threat-model and /triage.
Also in 5 projects that use this
MesteriisSkillsupply-chain-review
Reviews lockfiles, installers, provenance, CI permissions, dependency confusion, artifacts, registries, and publishing.
Also in 3 projects that use this
AnthropicSkillpatch
Generate candidate fixes for verified security findings. Consumes
Also in 4 projects that use this
mbwsimsSkillorbit
Run for repo-wide or diff-wide readiness sweeps: "/orbit", "/orbit pr", "/orbit deep", "/orbit quick", "audit this project", "project-wide review", "is this PR ready overall", or "combined security, tests, codebase, evolution, and instruction review". Use this for broad multi-system assessment, not for a single-file review or a one-domain question.
Also in 3 projects that use this
mbwsimsSkilltest-plan
This skill should be used when the user asks to "plan tests", "what should I test", "what tests do I need", "test plan for", "testing strategy for", "test matrix for", "what cases should I cover", "help me plan tests", mentions "/test-plan", or wants to understand what tests are needed before writing any test code.
Also in 3 projects that use this
Sagargupta16Skilldependency-audit
Audit project dependencies for security vulnerabilities, licensing issues, maintenance health, and optimization opportunities. Use it during regular security audits (monthly or quarterly); before a major release when you want to ensure the dependency tree is clean; when evaluating whether to adopt or replace a dependency; after a security advisory affects one of your dependencies; when your install times or bundle sizes have grown noticeably.
Also in 4 projects that use this
Other versions58 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 58
- openai/codex-security★ 14ksame name
- openai/plugins★ 7.8ksame name
- anthropics/defending-code-reference-harness★ 7.5ksame name
- Q00/ouroboros★ 6.4ksame name
- me2resh/apexyard★ 542same name
- jmanico/grim-prompter★ 497same name
- Cosmian/kms★ 372same name
- mbwsims/claude-universe★ 71same name
- navikt/copilot★ 61same name
- Codeminer42/skills★ 32same name
48 more not listed
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 repository23 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- ai-slop-cleanerSkill
- analyzeSkill
- askSkill
- autopilotSkill
- cancelSkill
- code-reviewSkill
- deep-interviewSkill
- deep-researchSkill
- doctorSkill
- hudSkill
- loftSkill
- modernizeSkill
- performance-goalSkill
- prSkill
- ralplanSkill
- releaseSkill
- skillSkill
- teamSkill
- ultragoalSkill
- ultraqaSkill
- visual-ralphSkill
- wikiSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 52 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Read references/stride-and-agentic-taxonomy.md before enumerating STRIDE categories, OWASP Agentic risks, or trust-boundary mitigations.
- Very specific: line 22
Evidence first, never generic filler: every threat entry must tie to real assets, entrypoints, configs, or observed file:line handlers in …
- Very specific: line 23
Never expose secrets: never echo .env values or literal tokens into artifacts.
- Very specific: line 35
Run sh <plugin>/hooks/run.sh mcp-audit <repo> --json to flag literal credentials in MCP headers/env, plaintext non-loopback http://, …
- Very specific: line 36
Run sh <plugin>/hooks/run.sh dep-license-diff <repo> --json and sh <plugin>/hooks/run.sh skill-validate ./skills --strict --json (if …
“Common” is measured: kept by at least 6 in 10 of the 52 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
Threat Model
Produce an evidence-backed, architecture-specific threat model for systems, services, AI/agentic toolchains, or high-risk features. Unlike $code-review (which checks a scoped PR diff) or $analyze (general debugging/diagnosis), $threat-model systematically models assets, actors, trust boundaries, STRIDE threats, OWASP LLM/Agentic Top-10 vectors, and concrete code-level mitigations grounded in observed file:line references.
Usage
$threat-model "target component, service, or whole repository"
$threat-model --scope auth "authentication, session, and webhook trust boundaries"
$threat-model --agentic "plugin hooks, MCP servers, and tool execution sandbox"Boundaries
- Read references/stride-and-agentic-taxonomy.md before enumerating STRIDE categories, OWASP Agentic risks, or trust-boundary mitigations.
- Read-only by default:
$threat-modelanalyzes code, manifests, configs, and schemas without editing application source unless the user separately asks to implement fixes. Save the deliverable to.omagy/artifacts/threat-model-{slug}-{YYYYMMDDTHHMMSSZ}.md. - Evidence first, never generic filler: every threat entry must tie to real assets, entrypoints, configs, or observed
file:linehandlers in the repo (or explicitly mark unverified runtime assumptions as inferred). - Never expose secrets: never echo
.envvalues or literal tokens into artifacts; run automated checks only against safe metadata (mcp-audit,dep-license-diff).
Workflow
Execute through parallel read-only reconnaissance (explore, security-reviewer, supply-chain-auditor, architect as scope warrants):
- Asset & Trust-Boundary Inventory:
- Identify protected assets (credentials/tokens, PII, tenant data, signing keys, filesystem/shell capabilities, payment/admin mutations).
- Map actors (unauthenticated external callers, authenticated low-privilege users, cross-tenant users, CI/build pipelines, untrusted external repos/web content, autonomous AI tools/MCP servers) and trust boundaries where privilege or data sanitization changes.
- Data-Flow Diagram (DFD):
- Draw a
flowchart LRMermaid diagram illustrating external inputs, API/CLI entrypoints, authz gates, storage/queues, MCP/subagent hops, and explicit trust boundaries (subgraph).
- Draw a
- Automated Config & Supply-Chain Pre-Checks:
- Run
sh <plugin>/hooks/run.sh mcp-audit <repo> --jsonto flag literal credentials in MCP headers/env, plaintext non-loopbackhttp://, filesystem root/..mounts, unpinned remote packages, and shell-metacharacter args. - Run
sh <plugin>/hooks/run.sh dep-license-diff <repo> --jsonandsh <plugin>/hooks/run.sh skill-validate ./skills --strict --json(if skills/plugins exist) for Trojan Unicode, hidden prompt-injection comments, or unpinned remote pipelines. - Inspect
.github/workflows/*.ymlfor overly broadpermissions:, pull-request-target script injection, or unpinned third-party actions (devops-engineer/supply-chain-auditor).
- Run
- Threat Enumeration (STRIDE + Agentic/LLM Top-10):
- Evaluate Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege across every crossing of a trust boundary.
- For AI/agentic/plugin/MCP systems, evaluate prompt injection (indirect HTML comments/external web/PR payloads), tool poisoning/shadowing, confused deputy filesystem/shell escapes, cross-session state bleed, path/symlink traversal, and untrusted
postMessage/ iframe sandbox leaks.
- Risk Matrix & Prioritized Mitigations:
- Score each threat (
LikelihoodxImpact->Critical | High | Medium | Low), record existing controls (file:lineverified), identify control gaps, and propose concrete, minimal-change mitigations with verification commands (test-engineer/runtime-qaprobes).
- Score each threat (
Output Deliverable Contract
Write .omagy/artifacts/threat-model-{slug}-{YYYYMMDDTHHMMSSZ}.md containing:
- Scope & Protected Assets table
- Trust-Boundary Mermaid
flowchart LRDFD - Automated Audit Findings (
mcp-audit,dep-license-diff, CI/workflow permissions) - Threat Register table (
ID,Category,Boundary/File,Threat Vector,Likelihood/Impact,Existing Control,Gap & Concrete Mitigation,Verification Test) - Top-5 Priority Actions & Out-of-Scope/Deferred Risks
Return the artifact path and concise Top-5 risk summary to the user.
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.

