react-19
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to query external documentation using the
mcp__context7__query-docstool. This is a standard feature for documentation-heavy skills but represents an indirect prompt injection surface if the external sources contain adversarial content.\n - Ingestion points: Documentation research step in
SKILL.md.\n - Boundary markers: None identified in the provided instructions.\n
- Capability inventory: Spawning sub-agents (
TeamCreate), code generation, and implementation validation (fuse-ai-pilot:sniper).\n - Sanitization: No explicit content validation or sanitization of the documentation search results is described.
Audit Metadata