batch-grill-me
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions defining an interview loop and design tree mapping. No malicious patterns, such as prompt injection, obfuscation, or hardcoded credentials, were detected.
- [SAFE]: While the instructions direct the agent to 'dispatch a sub-agent' and access 'filesystem, tools' to find facts, these are standard operational instructions for an AI agent and are not coupled with any specific dangerous payloads or unauthorized access attempts.
- [SAFE]: The skill includes a 'disable-model-invocation: true' frontmatter setting, which serves to restrict the agent's execution environment on compatible platforms, providing a defensive configuration.
Audit Metadata