intent-detection
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and analyzes untrusted user input to determine workflow routing.
- Ingestion points: User's first message (SKILL.md).
- Boundary markers: None explicitly defined to separate user data from instructions.
- Capability inventory: No execution capabilities; the skill only generates text suggestions for workflow commands.
- Sanitization: No validation or filtering is performed on the input text.
- [SAFE]: The skill contains no executable code, network operations, sensitive file access, or persistence mechanisms. The pseudo-code provided in the logic example is for behavioral guidance and does not involve command injection.
Audit Metadata