ship-it
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external command outputs, such as GitHub pull request information and test logs, which creates a surface for potential prompt injection from untrusted sources within the development environment.
- Ingestion points: Output from GitHub CLI commands (
gh pr list,gh pr view) and local verification/test commands (SKILL.md). - Boundary markers: The instructions do not specify delimiters or filtering logic for these external data streams.
- Capability inventory: The skill possesses capabilities for GitHub pull request management (
gh), branch manipulation, and local command execution for running tests (SKILL.md). - Sanitization: The skill explicitly instructs the agent to remove secrets and private data from evidence before publishing it to a pull request (SKILL.md).
Audit Metadata