help

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE] (SAFE): The skill does not exhibit any malicious patterns, obfuscation, or persistence mechanisms. Its logic is transparent and strictly aligned with its stated purpose of providing project help.
  • [COMMAND_EXECUTION] (LOW): The skill utilizes the Bash tool to perform simple directory listings (e.g., ls src/components/*.tsx) to verify project progress. These commands are hardcoded in the instructions and used only for informational purposes.
  • [PROMPT_INJECTION] (LOW): The skill processes untrusted data by reading project files like docs/PRD.md. This represents a potential indirect prompt injection surface. However, the instructions direct the agent to analyze the files for project state (e.g., checking if a template is empty) rather than executing instructions found within them, which significantly limits the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 05:04 PM