receiving-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to handle instructions provided in code review feedback from external reviewers. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions in review comments.
  • Ingestion points: External reviewer feedback and comments provided via GitHub or other review platforms.
  • Boundary markers: The skill does not define technical delimiters for reviewer input, relying instead on the agent's internal evaluation logic.
  • Capability inventory: The agent has the capability to execute grep commands, interact with the GitHub API (gh api), and modify the codebase by implementing suggestions.
  • Sanitization: The skill mandates a "verify before implementing" approach and technical skepticism, which serves as a manual verification layer but does not programmatically sanitize input.
  • [COMMAND_EXECUTION]: The skill mentions the use of grep for codebase analysis and the GitHub API for replying to PR comments. These are standard operations for a developer assistant and are used within the context of technical verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:28 AM