write
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via the context gathering phase. 1. Ingestion points: User-provided research, notes, and drafts are ingested as supporting material. 2. Boundary markers: The instructions lack explicit delimiters to separate user data from the core drafting logic. 3. Capability inventory: The skill performs text transformations and invokes sibling skills for voice and branding, but has no system or network access. 4. Sanitization: No sanitization or verification of the external content is performed.
Audit Metadata