grill-me
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, external downloads, or exfiltration attempts were detected.
- [NO_CODE]: The skill consists exclusively of instructions without any embedded executable scripts or commands.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it instructs the agent to read and process content from the local codebase.
- Ingestion points: Local codebase files (SKILL.md).
- Boundary markers: None specified to protect against instructions embedded in code or configuration files.
- Capability inventory: The skill relies on the agent's file-reading tools to resolve decision dependencies.
- Sanitization: No sanitization or validation of codebase content is mentioned.
Audit Metadata