code-reviewer

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is inherently exposed to indirect prompt injection as it is designed to process and analyze external, untrusted content such as pull requests, source code, and infrastructure manifests.
  • Ingestion points: The skill ingests user-provided source code, database migrations, Kubernetes manifests, and CI/CD configurations during the review process.
  • Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent treats the analyzed code strictly as data rather than instructions.
  • Capability inventory: The skill is instructed to integrate with AI-powered review tools, static analysis CLIs, and automated PR comment generation systems, which could be manipulated by embedded instructions in the code being reviewed.
  • Sanitization: No mention of input sanitization, filtering, or validation is present in the instructions to mitigate the risk of processing malicious instructions embedded in data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:44 PM
Security Audit — agent-trust-hub — code-reviewer