specialist-skill-routing
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task descriptions to route work to specialized agents.
- Ingestion points: The agent is instructed to scan the user's 'task description' for triggers.
- Boundary markers: No delimiters or warnings are provided to separate user content from the matching logic.
- Capability inventory: The skill facilitates the activation of various powerful specialized tools including package managers (uv), TUI frameworks (Textual), and MCP servers.
- Sanitization: The input description is scanned directly for trigger keywords without prior sanitization or filtering.
Audit Metadata