audit

audit is a skill for Claude Code from sonomoshq/Canary. It costs 31 tokens per session (523 once invoked), scanned A, original, MIT.

A security checker for installed coding-agent extensions, including plugins, skills, agents, and MCP settings. It looks for exposed secrets and patterns that could send data somewhere suspicious.

In plain words
What is it for?
Use it to audit extensions, review flagged files and severity levels, record findings, or make a strict check fail when critical issues are found.
Why use it?
It helps find credentials or unsafe data-collection behavior hidden in extension files before they are misused. Findings are summarized without showing the secret values.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the canary plugin — 5 skills, 1 agent, 3 hooks shipped together

Install

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.

Claude Code
/plugin marketplace add sonomoshq/Canary
Claude Code
/plugin install canary

Made for: Claude Code.

Or install canary, the plugin that ships this one along with the rest of its 5 skills, 1 agent, 3 hooks.

Wrote 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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonomoshq/canary/audit.svg)](https://agentmods.dev/skills/sonomoshq/canary/audit)
Your own site
<a href="https://agentmods.dev/skills/sonomoshq/canary/audit"><img src="https://agentmods.dev/badge/skills/sonomoshq/canary/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00523
Opus 5 $0.00015 $0.00262
Sonnet 5 $0.00006 $0.00105
Haiku 4.5 $0.00003 $0.00052

Measured 6d ago against content hash 768257faf45e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

canary/skills/audit/SKILL.md · 40 lines

What it actually says

Sonomos Extension Audit

Scan every installed skill, agent, plugin, and MCP/settings config for leaked secrets and suspicious exfiltration patterns — the same kind of PII/secret detectors Canary runs on your conversations, turned on the extensions themselves.

Run:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/audit-plugins.sh" $ARGUMENTS

$ARGUMENTS may be empty (report-only), --record (also append one leaks.jsonl summary line per flagged extension), --strict (exit 2 if anything CRITICAL was found), or both.

After it runs

Summarize the findings for the user in your own words:

  • Which extensions were flagged, their score/band (LOW/MEDIUM/HIGH/CRITICAL), and the top few findings for each (rule, severity, file:line when available).
  • Never print a raw secret value — the script's output is already redacted by detectors.sh; just relay what it printed.
  • If nothing was flagged, say so plainly — that's a good result.

Then suggest concrete next steps based on what was found:

  • Rotate any credential that showed up as a leaked secret (API key, token, private key) — assume it's compromised once it's sat in a plugin/skill file.
  • For CRITICAL findings (collector-domain, env-harvesting) or a CRITICAL-band extension, recommend removing or disabling that extension until it's been reviewed line by line.
  • For a finding that's actually a documented example or an intentional false positive, point out that adding # canary-ignore to that line (or, for .md files, putting it in a fenced code block introduced by a line containing the word "example") will suppress it on the next run.

Notes

  • This is a report-only tool: it never modifies the scanned files, and only writes to leaks.jsonl when --record is passed.
  • Canary's own plugin directory is skipped automatically — it legitimately ships the detector pattern library this audit is built on.

Copyright © 2026 Sonomos Inc. All rights reserved.

Changes

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.

  1. 6d ago First seen · 40 lines · 31 tokens per session scan A 768257faf45e

Subscribe to this mod's changes

audit is a skill published in the GitHub repository sonomoshq/Canary (2 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 523 once invoked, about $0.0002 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.

Related

Other skills, from other repositories