review-implementation

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to execute development tools such as cargo, git, eslint, and vulture to audit code quality and verify implementation. These are expected behaviors for a review-oriented skill.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and analyzes untrusted data from the codebase being reviewed.
  • Ingestion points: Reads source code files from src/ and tests/ directories and task specifications via bd show.
  • Boundary markers: No specific delimiters or safety instructions are used to separate the code content from the agent's internal instructions.
  • Capability inventory: Capable of executing shell commands, reading filesystem content, and triggering subsequent automated workflow steps.
  • Sanitization: The skill does not perform sanitization or filtering of the file content before interpreting it for review findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:19 PM