repo-maintenance-node

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect injection surface because it reads and acts upon data from the local repository and external GitHub PR titles.
  • Ingestion points: Files AGENTS.md, CLAUDE.md, and package.json are read to discover execution commands. GitHub PR titles are fetched via the gh CLI.
  • Boundary markers: None identified; the skill relies on the integrity of the repository configuration.
  • Capability inventory: The skill uses the Bash tool to run discovered scripts and performs git operations (add, commit).
  • Sanitization: No validation or escaping of the command strings extracted from configuration files is performed.
  • [COMMAND_EXECUTION]: Shell commands for repository health checks (like formatting and linting) are dynamically resolved from project manifests and then executed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:39 AM
Security Audit — agent-trust-hub — repo-maintenance-node