repo-cleanup

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the bash tool to perform essential cleanup tasks, including directory creation (mkdir), file movement (mv, git mv), and removal of build artifacts (rm -rf). It also performs git operations to prune merged branches and tag unmerged work for archival.
  • [EXTERNAL_DOWNLOADS]: The instructions recommend running several well-known Node.js utilities via npx (e.g., ts-prune, depcheck, unimported, license-checker) to identify unused exports, dependencies, and files within the codebase.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill analyzes content from the local repository to generate reports and determine cleanup actions. \n
  • Ingestion points: Content is read from source code, documentation, and configuration files using Read, Glob, and Grep tools. \n
  • Boundary markers: No specific delimiters are employed to isolate repository content from the agent's internal reasoning. \n
  • Capability inventory: The skill possesses the ability to modify the filesystem (Write, Edit) and execute shell commands (Bash). \n
  • Sanitization: Input data from the repository is not explicitly sanitized; however, the skill mandates safety procedures such as running tests, verifying builds, and obtaining user confirmation before proceeding with deletions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:13 PM