grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill is instructed to explore the codebase to answer questions in SKILL.md, which involves reading arbitrary files from the local project environment.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the codebase files are present.
- Capability inventory: The agent uses its standard file-reading and analysis tools to process the codebase.
- Sanitization: No explicit sanitization or validation of the codebase content is performed before the agent processes it for information.
Audit Metadata