agent-automation-smart-agent
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Prompt Injection (LOW): The skill exhibits an indirect prompt injection surface by ingesting untrusted natural language task descriptions to drive automated decisions. * Ingestion points: Natural language task descriptions and requirements analyzed in the 'Intelligent Task Analysis' module of SKILL.md. * Boundary markers: No delimiters or safety instructions are defined to separate user-provided data from agent instructions. * Capability inventory: The skill utilizes shell-based hooks (echo, memory_store) and possesses the high-level capability to spawn and configure new agents based on input. * Sanitization: There is no evidence of input validation or content filtering for the processed task requirements.
- Command Execution (SAFE): The pre and post hooks execute basic shell commands for initialization and status updates. These commands are static and do not incorporate or execute untrusted external input.
Audit Metadata