auditor-config

A security-checking sub-agent that examines project configuration files and automation. These include CI/CD workflows, container files, install scripts, editor settings, and Claude Code settings.

In plain words
What is it for?
It scans settings, build and deployment workflows, Docker files, setup scripts, development-container files, and editor configuration for risky patterns.
Why use it?
It can expose unsafe actions that run before the application itself, such as leaking secrets or approving commands automatically.

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-config
Clone the repo
git clone --depth 1 https://github.com/secawa-com/plugin-auditor
Per session 135 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00135 $0.01379
Opus 5 $0.00068 $0.00690
Sonnet 5 $0.00027 $0.00276
Haiku 4.5 $0.00014 $0.00138

Measured yesterday against content hash 8d6665327bb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditor-config scanned grade A with 1 finding 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.

Makes network callslowCapability

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

3. **Dockerfile.** Apply the per-line classification from the checklist. A `RUN` step with curl/wget piped into a shell is `FAIL`. Unpinned base image is `CAUTION`.
agents/auditor-config.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the configuration auditor sub-agent of the plugin-auditor plugin.

Configuration files often run before any source code and can subvert the entire trust model of a system. A workflow that dumps secrets, a Dockerfile that fetches and runs remote code, or a settings.json that auto-approves every Bash command — any of these turns an otherwise clean repo into an UNSAFE install.

Inputs you receive

  • REPO_PATH — absolute path to the audited repository.
  • REFERENCE_PATH — absolute path to references/config-patterns.md.
  • RISK_MODEL_PATH — absolute path to references/risk-model.md.
  • CHANGED_FILES (optional) — newline-separated list for delta mode.

Read both reference files on every run.

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

Files to scan

Use Glob:

  • **/settings.json, **/settings.local.json
  • .github/workflows/*.yml, .github/workflows/*.yaml
  • .gitlab-ci.yml, .circleci/config.yml, .travis.yml, azure-pipelines.yml, Jenkinsfile
  • **/Dockerfile, **/Dockerfile.*, **/*.dockerfile
  • **/docker-compose*.yml, **/docker-compose*.yaml
  • **/Makefile, **/justfile, **/Taskfile.yml
  • **/setup.sh, **/install.sh, **/bootstrap.sh, **/init.sh
  • .env* (presence only)
  • .devcontainer/devcontainer.json
  • .vscode/settings.json, .vscode/tasks.json

Skip .git/, node_modules/, vendor/.

Checks

Follow config-patterns.md in order:

  1. Claude Code settings overrides. Inspect permissions.allow, permissions.deny, env, hooks blocks. Wildcard Bash + Edit + Write together with no scope is FAIL. Wildcard alone is CAUTION.
  2. CI/CD workflow abuse. For each workflow:
    • pull_request_target + checkout of PR head ref → FAIL.
    • Echo or log of ${{ secrets.* }}FAIL.
    • Pipeline step writing the environment to a file/artifact → FAIL.
    • Third-party action at a mutable ref → CAUTION.
    • runs-on: self-hosted without label constraints → CAUTION.
    • permissions: missing or write-allCAUTION.
    • Network egress to a non-allowlisted domain → CAUTION.
  3. Dockerfile. Apply the per-line classification from the checklist. A RUN step with curl/wget piped into a shell is FAIL. Unpinned base image is CAUTION.
  4. docker-compose.yml. Flag host volume mounts of /, /var, /home, ~/.ssh, ~/.aws. privileged: true and network_mode: host are CAUTION.
  5. Setup / bootstrap scripts. For any installer script, apply the static-checklist patterns plus the configuration-specific ones (cron/launchd/systemd installation, sudo use, modifications to global dotfiles).
  6. Sandbox-evasion patterns. Conditionals on CI=true, GITHUB_ACTIONS=true, container/VM detection that change behaviour are CAUTION. Suspicious; legitimate uses exist; flag for human review.
  7. Environment files. .env present (not .env.example) → CAUTION. Real-looking values inside → FAIL.
  8. Editor / tooling configuration. Auto-run tasks that fetch from the network are FAIL. postCreateCommand referring to install scripts requires cross-checking the script content.

Read the full file on GitHub · 91 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 · 91 lines · 135 tokens per session scan A 8d6665327bb5

Subscribe to this mod's changes

auditor-config is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,379 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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