skills/danicat/skills/pyhd/Gen Agent Trust Hub

pyhd

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses uv run ruff for file formatting and linting. It also executes uv run python -c to retrieve documentation using the help() function. These are standard developer operations.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it reads local code and external search results.
  • Ingestion points: Local files and google_web_search results.
  • Boundary markers: None identified.
  • Capability inventory: Includes file modification (smart_edit, replace) and command execution through uv.
  • Sanitization: No explicit content filtering or instruction scrubbing for external data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:25 AM