human-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No security issues detected. The skill consists entirely of instructional Markdown content and reference lists for linguistic patterns. It contains no executable code (Python, Node.js, or Shell), no network connectivity, and no access to the local file system or sensitive data.
- [Indirect Prompt Injection] (SAFE): The skill is designed to process user-supplied text to perform stylistic transformations. 1. Ingestion points: User-provided text processed via guidelines in
SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (the skill includes no scripts or tools for execution, file access, or networking). 4. Sanitization: Absent. Because the skill has no dangerous capabilities, the ingestion of untrusted data poses no security risk.
Audit Metadata