caveman
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong instructions to ensure the agent maintains a specific communication style ('ACTIVE EVERY RESPONSE once triggered', 'No revert after many turns'). While these directives aim to override standard conversational patterns, they are intrinsic to the skill's primary function and do not target safety guardrails or attempt to extract system prompts.
- [SAFE]: The skill is strictly instructional and does not contain any executable scripts, binary files, or external dependencies.
- [SAFE]: No network activity, file system operations, or hardcoded credentials were detected.
- [SAFE]: The skill includes an explicit 'Auto-Clarity Exception' that instructs the agent to revert to normal communication for safety warnings and irreversible actions, which is a defensive best practice.
Audit Metadata