service-diagnosis
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's instructions.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external blueprint data.
- Ingestion points: The skill reads existing blueprint data from files (SKILL.md).
- Boundary markers: Absent; there are no instructions to the agent to treat content within the blueprint as non-executable data.
- Capability inventory: The skill is capable of writing generated diagnosis reports to project documentation folders.
- Sanitization: Absent; the skill does not specify any validation or sanitization for the ingested blueprint content.
Audit Metadata