ship
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of process guidelines for opening and managing pull requests. It does not involve any dangerous shell commands, network operations to untrusted domains, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and respond to CI check failure logs. This ingestion of external data is a potential attack surface for indirect prompt injection. 1. Ingestion points: CI failure logs (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Code modification and Git operations. 4. Sanitization: Absent.
Audit Metadata