skills/souliane/teatree/debug/Gen Agent Trust Hub

debug

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line utilities including git, grep, and ripgrep to perform necessary debugging tasks such as searching codebases and managing commit history.
  • [EXTERNAL_DOWNLOADS]: Contains a link to the obra/superpowers GitHub repository, referenced as an optional methodology companion.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted user hints and visual evidence (videos/screenshots).
  • Ingestion points: User text hints and visual media analyzed via t3 tool analyze-video in Phase 0 and 0b.
  • Boundary markers: None identified.
  • Capability inventory: Includes file system search (grep, rg), version control operations (git), and system commands (t3).
  • Sanitization: No explicit sanitization or input validation logic is present in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:00 AM