run-ts-cleanup

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Python 3 scripts (audit-ts-health.py, init-knip-config.py, batch-findings.py) to automate interactions with the system's package manager and various CLI utilities. It executes standard commands such as git, npx, tsc, knip, and madge to analyze the codebase and manage the cleanup process.
  • [EXTERNAL_DOWNLOADS]: The skill orchestrates the installation and execution of well-known TypeScript ecosystem tools (e.g., Biome, ESLint, Knip, Prettier) using npx. It also fetches configuration schemas from unpkg.com, a well-known CDN for npm packages. These downloads target official and established developer tools.
  • [INDIRECT_PROMPT_INJECTION]: As the skill is designed to ingest and analyze local source code and configuration files, it possesses a theoretical surface for indirect prompt injection via malicious content in the target repository. This risk is effectively managed through a disciplined wave-based remediation protocol that requires a clean baseline, human-in-the-loop triage of all findings, and mandatory verification gates before any changes are committed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 12:05 AM
Security Audit — agent-trust-hub — run-ts-cleanup