ship-pr
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues and implementation conversations to drive the pull request process. This represents an attack surface where malicious instructions embedded in an issue could potentially influence the agent's actions during the build or review stages.\n
- Ingestion points: Processes GitHub issue descriptions and conversation history as defined in
SKILL.md.\n - Boundary markers: No specific delimiters or safety warnings for untrusted input are defined in the orchestration instructions.\n
- Capability inventory: The skill manages pull request creation and pushing code fixes via its sub-skills (
implement-to-prandbabysit-pr).\n - Sanitization: There are no explicit sanitization or validation steps described for the input data.\n- [NO_CODE]: The skill consists of high-level workflow instructions and orchestration logic. It does not contain any scripts, binary executables, or direct shell command executions.
Audit Metadata