Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add akashsebastian333/peephole/plugin install peepholeWrote 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/akashsebastian333/peephole/sec-audit)<a href="https://agentmods.dev/skills/akashsebastian333/peephole/sec-audit"><img src="https://agentmods.dev/badge/skills/akashsebastian333/peephole/sec-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/akashsebastian333/peephole/sec-audit"><img src="https://agentmods.dev/badge/skills/akashsebastian333/peephole/sec-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 | $0.00066 | $0.00366 |
| Opus 5 | $0.00033 | $0.00183 |
| Sonnet 5 | $0.00013 | $0.00073 |
| Haiku 4.5 | $0.00007 | $0.00037 |
Grade A, and why
sec-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Peephole security audit
Run:
sh "$CLAUDE_PLUGIN_ROOT/hooks/peephole.sh" audit
Present the output to the user. It reports:
- mode and binary integrity (a drift alarm means the binary or its embedded KB was tampered with — advise reinstalling).
- decision tally — how many writes were denied / asked / allowed / retro-flagged / rewritten, broken down by CWE and by OWASP 2025 category.
- born-secure (N2) — of the security-relevant hunks (heuristic-tagged), how many were clean at first write vs prevented at the gate vs landed insecure, with the born-secure rate. Instrumentation, not proof.
- interruption rate — asks+denies per 20 write-gate decisions (the §7.4 FP budget: ≤ 1 unsolicited ask per 20 writes).
- sec-debt — logged waiver requests and any UNAPPROVED markers in the tree (evasion risk), plus negative-test mandates that exhausted without compliance.
- log chain —
intactorBROKEN at line N, which surfaces casual truncation or tampering of the decision log. The log is the last 30 days.
If the log chain is broken, treat it as a signal that the audit log was altered and tell the user plainly.
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.
- 11d ago First seen · 24 lines · 66 tokens per session scan A 0dd8875148ce
sec-audit is a skill published in the GitHub repository akashsebastian333/peephole (5 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 366 once invoked, about $0.0003 per session on Opus 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
assessing-vector-and-embedding-weaknesses
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
detecting-data-and-model-poisoning
Identify poisoned training data and backdoored models across the ML pipeline.
detecting-model-extraction-attacks
Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.
orchestrating-llm-attacks-with-pyrit
Build multi-turn, Crescendo, and Tree-of-Attacks-with-Pruning (TAP) automated attack chains against conversational LLM agents using Microsoft PyRIT, with adversarial chat and scorer feedback loops.
securing-agentic-ai-tool-invocation
Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.
continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.