code-review

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted code and metadata from GitHub pull requests.
  • Ingestion points: Pull request code and content processed for review (SKILL.md).
  • Boundary markers: Absent. There are no instructions to delimit untrusted content or ignore embedded instructions.
  • Capability inventory: The skill can modify pull request state by adding labels (add a 'code-reviewed' label).
  • Sanitization: Absent. The skill does not describe any validation or escaping of the input data.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform GitHub repository management tasks, specifically adding labels based on the identity of the user running the review.
  • [NO_CODE]: The skill contains only natural language instructions in markdown format and does not include any scripts, binaries, or configuration files that execute code directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:46 AM
Security Audit — agent-trust-hub — code-review