joke
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- General Analysis (SAFE): The skill consists entirely of natural language instructions for formatting joke responses. It contains no scripts, commands, or data access patterns.- Indirect Prompt Injection (INFO): While the skill processes user input (joke requests), it lacks any operational capabilities (e.g., network calls, file system writes, or subprocess execution) that could be leveraged for an attack.- Malicious Content (SAFE): No obfuscation, prompt injection overrides, or hardcoded credentials were found in the skill body or metadata.
Audit Metadata