peer-review

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and follow project-specific conventions from a 'DOJO.md' file and review arbitrary code files within a repository. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions in these files to attempt to override the agent's intended behavior or safety constraints.
  • Ingestion points: Reads 'DOJO.md' at the project root and any files identified within the git diff or specified review scope.
  • Boundary markers: The instructions do not define clear delimiters or warnings to the agent to ignore instructions found within the data being processed.
  • Capability inventory: The agent has the capability to read local files and execute git commands to determine review scope.
  • Sanitization: There is no explicit sanitization or validation of the content processed from project files or configuration documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 08:15 AM
Security Audit — agent-trust-hub — peer-review