code-review

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest and follow instructions found within the repository being reviewed, specifically files located in .github/instructions/**/*.instructions.md. This represents a surface where content within a repository could influence the agent's behavior during the review process.
  • Ingestion Points: The skill explicitly instructs the agent to read and apply instructions from the .github/instructions/ directory of the target repository.
  • Capability Inventory: The skill involves reading repository files, analyzing code changes, and reporting findings, which typically requires file system access and communication tools.
  • Boundary Markers: The current instructions do not include specific delimiters or warnings to help the agent distinguish between its core logic and instructions provided by the external repository.
  • Sanitization: There are no specific requirements listed for the agent to sanitize or validate the content of the repository-provided instruction files before application.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:31 AM
Security Audit — agent-trust-hub — code-review