code-review-quality

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes pull request data and source code, which are untrusted external inputs. This creates a surface for indirect prompt injection where malicious instructions embedded in code comments could influence the agent's behavior.
  • Ingestion points: Source code and metadata from pull requests are ingested via the coordination agents (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate processed code from the internal logic.
  • Capability inventory: The skill coordinates a fleet of specialized agents to perform logic, security, and performance scans.
  • Sanitization: No explicit sanitization or input validation steps are defined for the source code content before it is analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 05:55 PM