writing-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No security vulnerabilities or malicious patterns were identified. The skill is purely instructional.
- [NO_CODE] (SAFE): No scripts, commands, or external dependencies are included in the skill.
- [DATA_EXFILTRATION] (SAFE): No hardcoded secrets, sensitive file paths, or network communication patterns were detected.
- [PROMPT_INJECTION] (SAFE): No instructions targeting safety filter bypass or system prompt disclosure were found.
- [SAFE] (SAFE): Indirect Prompt Injection surface analysis: 1. Ingestion points: User provided text for drafting or editing. 2. Boundary markers: Absent. 3. Capability inventory: None (no shell, network, or file access). 4. Sanitization: Absent. The skill is non-exploitable due to zero capabilities.
Audit Metadata