add-feature

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows standard software development practices and does not contain instructions for data exfiltration, credential theft, or unauthorized network operations. Its scope is restricted to the local project files.
  • [COMMAND_EXECUTION]: The skill utilizes common Node.js development commands, specifically npm run build and npm run dev, to compile and verify the new features. These are expected behaviors for a coding assistant tool.
  • [PROMPT_INJECTION]: The skill incorporates user-provided feature descriptions via the $ARGUMENTS parameter, which presents an indirect prompt injection surface. Ingestion points: The feature description is read directly into the step-by-step instructions. Boundary markers: No explicit markers are used to isolate user input from the skill's logic. Capability inventory: The agent can modify project files and execute build scripts. Sanitization: No sanitization is performed on the user input, though the impact is mitigated by the skill's adherence to existing code patterns and the requirement to pass a build step.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:54 PM