gate-ai
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies user needs to route them to specific workflows, creating a surface where user-supplied instructions could influence behavior.
- Ingestion points: The skill takes '用户需求' (User demand) as input from the user in SKILL.md.
- Boundary markers: No boundary markers or 'ignore' instructions are used to separate user input from skill logic.
- Capability inventory: The skill focuses on routing to other workflows (e.g., ai-coding-workflow, ai-testing) and does not exhibit dangerous capabilities like direct command execution or network access.
- Sanitization: Input is passed through to routing logic without sanitization or validation.
Audit Metadata