client-alert-drafting
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns or security risks identified. The skill is entirely declarative and focuses on writing style and document structure.- [Indirect Prompt Injection] (SAFE): The skill processes legal development data which constitutes an ingestion surface, but the risk is negligible as the skill lacks high-privilege capabilities such as code execution or network exfiltration. Ingestion points: Workflow step 1 (Gather information) in SKILL.md. Boundary markers: Not explicitly defined in the template. Capability inventory: Mentions calling an external docx skill for output generation; no internal command or network execution detected. Sanitization: No input validation or escaping procedures are specified.
Audit Metadata