grill-me
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no malicious patterns, obfuscation, or unauthorized access attempts. It provides benign instructions for the agent to interview the user one question at a time and explore the local codebase to resolve design dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it instructs the agent to ingest data from the codebase. However, this is a standard capability for development-focused agents and is handled by the platform's core safety layers.
- Ingestion points: The skill instructs the agent to "explore the codebase" in SKILL.md.
- Boundary markers: None specified in the instructions.
- Capability inventory: The agent uses platform tools to explore files (e.g., ls, grep, read_file).
- Sanitization: No explicit sanitization or filtering of codebase content is mentioned.
Audit Metadata