project-flow-ops
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions without any associated scripts or executable components.\n- [PROMPT_INJECTION]: Analysis of indirect prompt injection surface reveals the skill processes external data from GitHub (issues, pull requests, and comments). This is a functional requirement of the skill.\n
- Ingestion points: GitHub PR/issue descriptions, comments, and CI status are gathered in SKILL.md.\n
- Boundary markers: The instructions do not specify delimiters for external content.\n
- Capability inventory: The skill's capabilities are limited to logical classification and status reporting; it contains no shell execution, file system modifications, or direct network operations.\n
- Sanitization: No explicit sanitization of ingested text is performed.
Audit Metadata