shunk031-github-cgd-identity

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions depend on an external utility named setup-gh-cgd. While the implementation of this command is not included in the skill files, the instructions direct the agent to execute it for authenticating the machine user account.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with external data from GitHub repositories, such as pull request descriptions and issue comments. This creates a potential surface where malicious instructions hidden in that data could influence the agent's actions.
  • Ingestion points: The skill performs write operations (commits, PR creation, comments) based on content within the creative-graphic-design organization repositories.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions contained within the external GitHub data being processed.
  • Capability inventory: The skill allows the agent to perform git commits, pushes, and various GitHub API operations using a machine user token.
  • Sanitization: The skill does not provide methods for sanitizing or validating external input before it is used in commands or API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 04:07 AM
Security Audit — agent-trust-hub — shunk031-github-cgd-identity