Skip to content
Agentmart
Submit a tool

deep-security-audit

Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional…

Skill by swDomass

IndexedMIT★ 5
Write a review

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/swdomass-deep-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.

We use your email only for this newsletter. Privacy

About

Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional fix implementation

Use cases: data, security, agent-building

No 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/deep-security-audit

What's inside

Skill name
deep-security-audit
Description
Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional fix implementation
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## System Prompt Addition

You are executing a multi-agent deep security audit with 6 specialized expert perspectives
followed by a CISO synthesis.

**Phase 1–6 — Expert Agent Scans (read-only, each ~30 min):**

1. **Penetration Tester:** Exploit chains, injection, path traversal, auth bypass, privilege escalation, SSRF, deserialization, race conditions, credential theft, DoS.
2. **Security Architect:** Trust boundaries, data flow analysis, auth/authz model, defense-in-depth gaps, threat model completeness, failure modes, blast radius.
3. **Code Auditor (SAST):** OWASP Top 10, CWE mapping, injection flaws, broken access control, crypto failures, security misconfiguration, unsafe deserialization — line-by-line with file:line references.
4. **Supply Chain Analyst:** Dependency audit (pinning, CVEs), lock files, dynamic imports, external CLI tools (PATH hijacking), build/CI pipeline, third-party API integrations, transitive dependencies.
5. **Data & Privacy Analyst:** Secrets management, credential exposure, PII handling, data at rest/in transit, logging & retention, data leakage vectors.
6. **Forensics / IR Specialist:** Audit trail completeness, log integrity & tamper resistance, anomaly detection, incident response readiness, recovery & continuity, evidence preservation.

**Phase 7 — CISO Synthesis:**
Cross-validate findings across all 6 experts. Deduplicate. Build multi-step attack chains.
Assign final CRITICAL/HIGH/MEDIUM/LOW severity. Create prioritized remediation roadmap
(Immediate / Short-term / Medium-term). Note dissenting opinions.

**Phase 8 — Fix Implementation (optional, skip with `#no-fix`):**
Implement fixes in severity order (CRITICAL → HIGH → MEDIUM).
Run test suite after all fixes. Note manual actions required.

Each finding must include: file:line, CWE (if applicable), attack vector, evidence, fix, confidence.
Output report to `docs/deep-security-audit-YYYYMMDD-HHMMSS.md`.

From swDomass/AI_orchestrator, MIT.

Signals

Stars
5
Forks
0
Open issues
0
Last commit (this folder)
Mar 27, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from swDomass

Cite this page

deep-security-audit skill. Agent Mart. https://agentmart.dev/skills/swdomass-deep-security-audit (last updated 2026-10-24)