run-ts-cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill's Python scripts (
audit-ts-health.py,batch-findings.py,init-knip-config.py) use thesubprocessmodule to run development commands such asnpx,git, and various package managers. These are necessary for the skill's operation in analyzing and modifying codebases. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external, potentially untrusted source code and documentation. While it includes triage steps and uses deterministic linters, the ingestion of untrusted code for 'AI slop' detection provides an attack surface for indirect prompt injection.
- [EXTERNAL_DOWNLOADS]: The documentation suggests the optional use of an external tool from a third-party GitHub repository (
dmmulroy/anti-slop) to assist in detecting LLM-generated code patterns.
Audit Metadata