code-reviewing

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze untrusted code changes and pull request data, creating a surface for indirect prompt injection where malicious instructions could be embedded in code comments or strings.
  • Ingestion points: The skill intakes and processes code diffs, PR descriptions, and repository content (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to separate untrusted code data from the agent's logic.
  • Capability inventory: No tool use, subprocess execution, file system modification, or network access capabilities are defined within this skill.
  • Sanitization: There are no explicit sanitization or filtering steps specified for the code content being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:26 PM
Security Audit — agent-trust-hub — code-reviewing