init
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No executable scripts or binary files are included with this skill. It consists entirely of natural language instructions for the agent.\n- [PROMPT_INJECTION]: The skill processes content from the repository, which creates a surface for indirect prompt injection if analyzed files contain malicious instructions. Ingestion points: READMEs, manifests, and project configuration files (SKILL.md). Boundary markers: Absent. Capability inventory: Reading repository files and writing results to AGENTS.md. Sanitization: Absent. This surface is inherent to the task of codebase analysis.
Audit Metadata