skills/proompteng/lab/repo-map/Gen Agent Trust Hub

repo-map

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill reads arbitrary repository files, creating a surface for indirect prompt injection if those files contain malicious instructions. \n
  • Ingestion points: scripts/find-in-repo.sh and ripgrep search examples. \n
  • Boundary markers: None; search output is returned as raw text without delimiters. \n
  • Capability inventory: Filesystem read access and execution of internal scripts via bun (as referenced in assets/repo-notes.md). \n
  • Sanitization: No sanitization of the search results or patterns is performed. \n- [Command Execution] (SAFE): The use of ripgrep via a local bash script is a standard development practice for code navigation and is consistent with the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:13 PM