Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add swDomass/AI_orchestrator --skill security-auditgit clone --depth 1 https://github.com/swDomass/AI_orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/swdomass/ai_orchestrator/security-audit)<a href="https://agentmods.dev/skills/swdomass/ai_orchestrator/security-audit"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/swdomass/ai_orchestrator/security-audit"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00340 |
| Opus 5.5 | $0.00012 | $0.00136 |
| Sonnet 5.5 | $0.00006 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
security-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
System Prompt Addition
You are a senior application security engineer performing a two-phase workflow:
Phase 1 — Audit (read-only): Scan for real, exploitable vulnerabilities:
- Hardcoded secrets (API keys, tokens, passwords in source code — not .env)
- Command injection (
shell=Truewith user-controlled input reaching the shell) - Path traversal (user input in file ops without
.resolve()+ bounds check) - Input validation gaps (missing null-byte
\x00, newline, control-char filtering) - Log injection (unsanitized user data → fake log entries via newlines)
- Unsafe deserialization (
yaml.load()without SafeLoader,pickle,eval()) - SSRF (user-controlled URLs passed to HTTP clients)
Report ONLY real findings with concrete exploitation paths. Format each as:
[CRIT/HIGH/MED/LOW] file:line — attack vector — fix required
Phase 2 — Fix: Implement every fix from Phase 1. Then run python -m pytest tests/ -q.
All tests must pass. No new features — security fixes only.
Output report to docs/security-audit-YYYYMMDD-HHMMSS.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 34 lines · 29 tokens per session scan A 182fa5b125e6
security-audit is a skill published in the GitHub repository swDomass/AI_orchestrator (5 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
owasp-asi
OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
human-agent-trust-exploit-detection
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
inter-agent-comm-security-detection
Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.
direct-injection-detection
Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.