Codebase Argus

PassAudited by ClawScan on May 10, 2026.

Overview

Codebase Argus is a coherent PR/CI review playbook that discloses optional GitHub and AI-provider credentials plus webhook automation, but users should configure those powers carefully.

Before installing, verify the external Codebase Argus checkout, use read-only or least-privileged credentials, restrict any GitHub App to the intended repositories, and only send private code or logs to AI providers if your policy allows it.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Running the npm commands may execute package scripts or review code that ClawScan did not inspect here.

Why it was flagged

The registry entry is instruction-only, so these commands depend on code from an external checkout that was not included in the reviewed artifacts.

Skill content
From a Codebase Argus checkout:

npm install
npm run argus -- review owner/repo#123
Recommendation

Install only from a trusted repository or pinned commit, inspect package scripts and lockfiles first, and prefer a sandboxed environment.

What this means

These credentials can expose private repositories, CI logs, provider accounts, or GitHub App authority if over-scoped or mishandled.

Why it was flagged

The skill documents optional GitHub, GitHub App, and AI-provider credentials used for private repositories, Actions logs, provider review, and webhook deployment.

Skill content
GITHUB_TOKEN=<read-only-token> ... OPENAI_API_KEY=<key> ... ANTHROPIC_API_KEY=<key> ... GEMINI_API_KEY=<key> ... GITHUB_APP_PRIVATE_KEY=<pem-or-escaped-pem>
Recommendation

Use least-privilege tokens, restrict GitHub App installation to intended repositories, avoid broad write permissions, and follow the skill’s instruction not to print or write tokens to files.

What this means

If deployed with excessive permissions or exposed to untrusted command use, the automation could create unwanted PR comments or labels.

Why it was flagged

The webhook can post PR review comments, add inline comments, and mutate a pause label. This is disclosed and bounded, but it affects GitHub collaboration state.

Skill content
posts COMMENT reviews only, and can add inline comments when ARGUS_WEBHOOK_INLINE_COMMENTS=true ... /argus pause applies `argus:paused`; automatic review skips PRs with that label.
Recommendation

Deploy with minimal GitHub App permissions, restrict comment commands to trusted users where possible, and keep automatic actions limited to comment-only review unless explicitly approved.

What this means

Private code, PR diffs, or CI logs could be shared with configured AI providers or local CLI agents.

Why it was flagged

The playbook supports sending code-review evidence to external API providers or multiple local/remote agent providers.

Skill content
Both upstream and downstream workflows can send the same evidence package to one provider or a multi-agent tribunal.
Recommendation

Use provider review only when allowed by your repository’s data policy, avoid including secrets in logs, and use local CLI providers only in trusted workspaces as the skill advises.

What this means

After deployment, the automation may continue posting review comments on future PR events until paused, disabled, or uninstalled.

Why it was flagged

A deployed webhook server is intended to operate continuously on GitHub PR events. The behavior is disclosed, signature-verified, and pausable.

Skill content
For automatic PR review, the deployed Next.js server exposes:
POST /api/github/webhook
Recommendation

Deploy only when ongoing PR automation is desired, monitor its comments, use the pause/resume controls, and remove the webhook or app installation when no longer needed.