codebase-cleanup-audit

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a legitimate utility for codebase maintenance, utilizing local Node.js scripts for file system traversal and content analysis without external network access. Findings are stored locally in a scratch directory within the scanned project root.\n- [COMMAND_EXECUTION]: The skill executes a local Node.js script to generate audit snapshots. This execution is scoped to the project root and facilitates the primary purpose of the skill within the user's local environment.\n- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests and summarizes untrusted project data (e.g., comments like TODO or FIXME).\n
  • Ingestion points: Content signals and function bodies are extracted from local files in scripts/inventory.mjs and scripts/function-scanner.mjs.\n
  • Boundary markers: The audit reports (HTML and Markdown) provide findings without isolated boundary delimiters for the extracted code snippets.\n
  • Capability inventory: The skill uses standard file system access to read project files and write reports, instructing the agent to recommend deletions based on the audit results.\n
  • Sanitization: The tool escapes HTML entities in its report output to prevent cross-site scripting in browser-based views.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 11:48 AM
Security Audit — agent-trust-hub — codebase-cleanup-audit