Skills
Navigate
skills/kenryu42/cc-safety-net/ccsn-no-comments/Gen Agent Trust Hub

ccsn-no-comments

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from code comments and git history which could contain instructions intended to influence the agent.
  • Ingestion points: Reads file content, git blame output, and git logs in the cc-safety-net repository.
  • Boundary markers: No specific delimiters or warnings are used to separate external comment text from the agent's internal logic.
  • Capability inventory: The agent has the ability to execute shell commands (bun, git) and modify repository files.
  • Sanitization: No sanitization or filtering of the comment content is performed before processing.
  • [COMMAND_EXECUTION]: The skill requires the execution of several shell commands to perform its tasks, including bun run lint:comments, bun run check, git blame, and git log.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:39 AM