writing-maestro
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns, hardcoded secrets, or suspicious network operations were detected. The skill's behavior is consistent with its stated purpose of prose refinement.
- [NO_CODE]: The skill consists of YAML configuration and Markdown reference files. It does not contain any Python, JavaScript, or other executable scripts.
- [PROMPT_INJECTION]: The skill processes untrusted data. 1. Ingestion point: Untrusted human-facing prose such as docs, essays, and reports (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Text drafting, rewriting, and editing (SKILL.md). 4. Sanitization: Absent. While this creates a surface for indirect prompt injection, the lack of dangerous capabilities like network or file system access minimizes the risk.
Audit Metadata