grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains benign instructions and does not perform any network operations, access sensitive credentials, or attempt to modify the system.
- [NO_CODE]: No executable code, scripts, or binary files are included with this skill; it consists entirely of markdown-based instructions.
- [PROMPT_INJECTION]: Indirect Prompt Injection surface analysis: 1. Ingestion points: The agent is instructed to explore the codebase (SKILL.md); 2. Boundary markers: None; 3. Capability inventory: Codebase exploration and answering questions (SKILL.md); 4. Sanitization: No explicit sanitization of codebase content is mentioned. This surface is a standard requirement for the skill's functionality and carries minimal risk.
Audit Metadata