grilling
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on structured interviewing and logical plan validation. No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by instructing the agent to explore the codebase for facts. This behavior is standard for development agents but could allow malicious instructions inside the codebase to influence the agent's behavior during the 'grilling' process.
- Ingestion points: Reads files from the user's codebase (SKILL.md).
- Boundary markers: None explicitly defined in the skill instructions to separate code content from instructions.
- Capability inventory: Uses read-access tools to explore the codebase as mentioned in the logic.
- Sanitization: No specific sanitization or validation of the codebase content is performed before processing.
Audit Metadata