lovstudio-gh-contribute
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill orchestrates repository workflows by executing shell commands via the
gitandgh(GitHub CLI) tools. It uses variables derived from the local environment and repository metadata, such as$UPSTREAMand$BRANCH_NAME, to perform actions like forking, pushing code, and creating pull requests. - [PROMPT_INJECTION]: The skill processes untrusted content from external repositories, which creates a surface for indirect prompt injection.
- Ingestion points: In Step 2, the skill fetches the contents of
CONTRIBUTING.md,CODE_OF_CONDUCT.md, and pull request templates from the targeted upstream repository. - Boundary markers: The instructions do not specify the use of delimiters or clear separation markers to distinguish between the skill's core instructions and the external data being ingested.
- Capability inventory: The skill has access to powerful capabilities, including modifying the local filesystem through
git commitand performing network-authenticated actions such asgit pushandgh pr create. - Sanitization: No explicit sanitization or validation logic is defined to check the external content before the agent evaluates it for contribution rules and formatting constraints.
Audit Metadata