lov-gh-contribute
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the upstream repository during its execution workflow.
- Ingestion points: The skill fetches
CONTRIBUTING.md,CODE_OF_CONDUCT.md, and PR templates directly from the upstream repository (viagh api) to determine project-specific rules. - Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings when processing these external documents.
- Capability inventory: The skill utilizes
gitandghcommands, which provide significant capabilities for file system modification (git commit,git checkout), network operations (git push), and repository management (gh pr create). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the upstream repository before it is used to influence the agent's behavior.
- [COMMAND_EXECUTION]: The skill relies on several shell commands to perform its core tasks.
- It executes
gitfor branch management, diffing, committing, and pushing. - It executes the
ghCLI for interacting with the GitHub API, forking repositories, and creating pull requests.
Audit Metadata