create-pr-commit
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from repository documentation and history to determine naming conventions.
- Ingestion points: The skill reads README, CONTRIBUTING, .github/ folder configurations, and git history logs.
- Boundary markers: There are no instructions provided to the agent to disregard potentially malicious instructions embedded within the analyzed files.
- Capability inventory: The skill's output is restricted to generating text suggestions; it does not possess the ability to perform file writes, execute commands, or initiate network connections.
- Sanitization: The skill does not specify any sanitization or validation logic for the content it ingests from the repository.
- [NO_CODE]: The skill is composed entirely of markdown instructions and does not include any executable scripts or binaries.
Audit Metadata