grilling
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content for a logical interaction workflow. No malicious patterns, obfuscation, or suspicious behaviors were detected.
- [PROMPT_INJECTION]: The instructions are designed to constrain the agent's interaction style (one question at a time) and do not attempt to bypass safety guidelines or override systemic instructions.
- [DATA_EXFILTRATION]: While the skill reads project context (code and documents) to inform the interview process, it lacks any network-facing tools or commands to transmit data externally.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level operations are defined within the skill or its references.
Audit Metadata