techdoc-search-and-orchestrate
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a task delegation pattern to manage context tokens. It instructs the agent to use a specialized sub-agent (context7-researcher) for technical queries instead of direct tool usage in the main conversation. This is a standard architectural design for complex AI agents.
- [PROMPT_INJECTION]: While the skill contains directive language (e.g., 'Mandatory', 'Forbidden') to enforce its research workflow, these are standard prompt engineering techniques used for task routing and do not attempt to bypass security filters or disclose system prompts.
- [DATA_EXFILTRATION]: No sensitive file paths or unauthorized network operations were detected. The skill's operations are limited to routing technical queries within the local agent environment and do not involve credential harvesting or data transmission to external domains.
Audit Metadata