shunk031-github-cgd-identity
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
gitandghCLI tools to perform GitHub operations. It implements security best practices by using transient environment variables for authentication tokens instead of persistent shell exports or global configuration changes. - [INDIRECT_PROMPT_INJECTION]: Because the skill is designed to interact with GitHub issues and pull requests, it processes external user-generated content (comments, issue bodies). While this is an inherent attack surface for indirect injection, the skill's instructions focus strictly on the identity management layer and do not include unsafe interpolation patterns.
- [PROMPT_INJECTION]: The file contains a directive for the agent to output a specific confirmation string after reading. This is a common behavioral verification pattern and does not attempt to bypass safety guardrails or override core instructions.
Audit Metadata