task-planner
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of markdown-based instructional content. It does not contain any scripts, binaries, or configuration files that execute logic on the host system.
- [Data Exposure & Exfiltration] (SAFE): No patterns for file system access, credential harvesting, or network communication were identified.
- [Prompt Injection] (SAFE): The text does not contain any instructions intended to bypass safety filters, extract system prompts, or override agent behavior.
- [Indirect Prompt Injection] (INFO): While the skill is designed to process external task descriptions, it lacks any 'write' or 'execute' capabilities (e.g., shell access, file modification) that could be leveraged by a malicious input to cause harm.
Audit Metadata