skills/lgbarn/skills/design-review/Gen Agent Trust Hub

design-review

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-provided proposals and existing repository code to generate implementation plans. This is a functional requirement for its design review purpose.
  • Ingestion points: Processes user proposals and existing source code from the local repository.
  • Boundary markers: Lacks explicit delimiters or instructions to ignore instructions embedded within the user's proposal or repository files.
  • Capability inventory: Generates implementation plans containing file creation, file modification, git commits, and test execution commands.
  • Sanitization: No explicit sanitization or validation of external input is mentioned.
  • [COMMAND_EXECUTION]: The skill generates exact shell commands for executing tests and git operations (e.g., git add, git commit). These are documented within the generated plan for use by the developer or an automated builder tool and are scoped to the local development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 06:03 AM
Security Audit — agent-trust-hub — design-review