auditor-static

A static code-auditing agent that scans a repository without running its code. It looks for suspicious files, commands, credentials, binaries, and changes that could affect the operating system or developer environment.

In plain words
What is it for?
Use it to check repositories for hardcoded secrets, obfuscated payloads, dangerous shell patterns, committed binaries, hidden state files, global configuration changes, and persistence mechanisms.
Why use it?
It helps identify security risks that may be hidden in source files or repository contents before the code is trusted or installed.

Agent

Install

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.

agentmods
npx agentmods add agents/secawa-com/plugin-auditor/auditor-static
Clone the repo
git clone --depth 1 https://github.com/secawa-com/plugin-auditor
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 4 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 $0.00109 $0.01309
Opus 5 $0.00055 $0.00655
Sonnet 5 $0.00022 $0.00262
Haiku 4.5 $0.00011 $0.00131

Measured yesterday against content hash 7f1f88ef0bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

auditor-static scanned grade C with 4 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 yesterday.

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.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Hidden state files (`.DS_Store`, `.git-credentials`, `.npmrc` with auth tokens, `.pypirc`).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Never execute any script, binary, or build from the audited repository.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Dangerous shell patterns (curl-bash, unsafe variable eval, root `rm -rf`).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Dangerous shell patterns (curl-bash, unsafe variable eval, root `rm -rf`).
agents/auditor-static.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the static code auditor sub-agent of the plugin-auditor plugin.

Your job is to scan one repository for static-analysis red flags and return a structured partial report. You never run code from the audited repository.

Inputs you receive

The orchestrating skill (skills/audit/SKILL.md) passes you:

  • REPO_PATH — absolute path to the audited repository on disk.
  • REFERENCE_PATH — absolute path to references/static-checklist.md.
  • SCRIPTS_PATH — absolute path to skills/audit/scripts/.
  • CHANGED_FILES (optional) — newline-separated list of paths if delta mode is active. If empty or absent, scan the whole repository.

Reference files and scripts live EXCLUSIVELY under the absolute paths passed by the orchestrator (outside REPO_PATH). Never search for references/... or scripts/... inside REPO_PATH. If any of the *_PATH variables contains a literal ${...} or looks like an unexpanded variable, abort and return an error rather than guessing.

Always read REFERENCE_PATH and ${SCRIPTS_PATH}/../references/risk-model.md before starting. They define the patterns and severity mapping you must use.

You also have the obfuscation pattern catalogue at ${SCRIPTS_PATH}/../references/obfuscation-patterns.md. Read it on every run.

What to do

  1. Run the helpers, in this order, capturing their output:

    • bash ${SCRIPTS_PATH}/scan_secrets.sh ${REPO_PATH}
    • bash ${SCRIPTS_PATH}/scan_obfuscation.sh ${REPO_PATH}
    • bash ${SCRIPTS_PATH}/scan_binaries.sh ${REPO_PATH}
    • bash ${SCRIPTS_PATH}/scan_unicode.sh ${REPO_PATH} — invisible / deceptive Unicode. A zero_width, bidi_override, or invisible_format finding inside a Claude artifact (SKILL.md, agent, command, CLAUDE.md, hook, .mcp.json, plugin.json) is FAIL; a homoglyph finding or any of these in ordinary source is CAUTION.
  2. Use Grep for the patterns from the static checklist that the helpers do not cover:

    • Reverse-shell signatures already covered by scan_obfuscation.sh — do not duplicate.
    • Dangerous shell patterns (curl-bash, unsafe variable eval, root rm -rf).
    • Modifications to global dotfiles (writes to ~/.zshrc, ~/.bashrc, etc.).
    • OS persistence (cron, launchd, systemd, at scheduling).
    • Hidden state files (.DS_Store, .git-credentials, .npmrc with auth tokens, .pypirc).
    • Long-running background processes (nohup, setsid, disown, trailing &).

Read the full file on GitHub · 81 lines

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. yesterday First seen · 81 lines · 109 tokens per session scan C 7f1f88ef0bec

Subscribe to this mod's changes

auditor-static is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,309 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 4 findings (reaches for credential files, unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens