security-audit
Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates.
Skill by mateim4
Chalk Labs
Need help deploying security-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mateim4-security-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/security-audit
What's inside
- Skill name
security-audit- Description
- Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates. Use for a security-only pass.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# AgentStrap security audit A security-focused subset of `/agentstrap:audit`. ## Step 0 — Deployment context Use the argument if given, else `.agentstrap/config.json` `audit.deployment_context`, else default `internet-facing`. This drives the severity badges (🔴 APPLIES / 🟡 REDUCED / ⚪ N/A) shown in the scale below. ## Step 1 — Dispatch (parallel) Dispatch `audit-security` and `audit-adversarial` via the Task tool, scoped to the code. **In each task prompt include** the severity scale, the deployment context, and the finding format: > **P0** exploitable now / data loss · **P1** serious defect, fix now · **P2** real but not urgent · **P3** polish. Tag **STRIDE** (Spoofing/Tampering/Repudiation/Info-disclosure/DoS/Elevation) + badge 🔴 APPLIES / 🟡 REDUCED / ⚪ N/A per deployment context (default `internet-facing` = 🔴). Both tag findings with STRIDE + a context badge. ## Step 2 — Consolidate and report Run the `consolidate-findings` steps. Group by STRIDE category and tier. Compare against any previous security audit in the vault and flag regressions / fixes / new findings. Write the report to `30 - Engineering/Audits/Security Audit YYYY-MM-DD.md` (or print). Review only — do not change code unless asked.
From mateim4/agentstrap-v2, MIT.
More from mateim4/agentstrap-v2
- 0.524score
decision
mateim4
Record an architectural/product decision in the project's Decisions Log (append-only, newest first).
SkillBFreshness: BClaude Code +9 - 0.524score
handoff
mateim4
Force a full handoff refresh now — write a thorough narrative of where work stands into HANDOFF.md so the next session (or device) resumes cleanly.
SkillBFreshness: BClaude Code +9 - 0.521score
working-rules
mateim4
The AgentStrap PM-first collaboration contract — how Claude should drive an AgentStrap project.
SkillBFreshness: BClaude Code +9 - 0.520score
bootstrap
mateim4
Bootstrap or sanity-check an AgentStrap workspace in this project — idempotent and non-destructive.
SkillBFreshness: BClaude Code +9 - 0.474score
release
mateim4
Run the AgentStrap release pipeline — bump all version files, finalize the changelog, build, gate on tests, tag, and write checksums.
SkillCFreshness: CClaude Code +9 - 0.474score
audit
mateim4
Run the AgentStrap audit swarm over the codebase — fan out specialist reviewers in parallel, then consolidate into a deduped P0–P3 report.
SkillCFreshness: CClaude Code +9 - 0.471score
open-question
mateim4
Add or resolve an entry in the project's Open Questions register.
SkillCFreshness: CClaude Code +9 - 0.467score
consolidate-findings
mateim4
Reduce step for the audit swarm — dedupe findings from multiple reviewers, assign stable IDs, normalize to P0–P3, and group into prioritized batches with a…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 14, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mateim4/agentstrap-v2
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mateim4
- 0.524score
decision
mateim4
Record an architectural/product decision in the project's Decisions Log (append-only, newest first).
SkillBFreshness: BClaude Code +9 - 0.524score
handoff
mateim4
Force a full handoff refresh now — write a thorough narrative of where work stands into HANDOFF.md so the next session (or device) resumes cleanly.
SkillBFreshness: BClaude Code +9 - 0.521score
working-rules
mateim4
The AgentStrap PM-first collaboration contract — how Claude should drive an AgentStrap project.
SkillBFreshness: BClaude Code +9 - 0.520score
bootstrap
mateim4
Bootstrap or sanity-check an AgentStrap workspace in this project — idempotent and non-destructive.
SkillBFreshness: BClaude Code +9 - 0.474score
release
mateim4
Run the AgentStrap release pipeline — bump all version files, finalize the changelog, build, gate on tests, tag, and write checksums.
SkillCFreshness: CClaude Code +9 - 0.474score
audit
mateim4
Run the AgentStrap audit swarm over the codebase — fan out specialist reviewers in parallel, then consolidate into a deduped P0–P3 report.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get security-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
security-audit skill. Agent Mart. https://agentmart.dev/skills/mateim4-security-audit (last updated 2026-10-24)