human-authored-writing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and references are purely focused on writing style and clarity. There are no executable scripts, tool invocations, or commands that could lead to unauthorized system access or data exposure.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text, representing an indirect injection surface. 1. Ingestion points: User-provided drafts, outlines, and fragments ingested during the writing process as described in references/current-guidance.md. 2. Boundary markers: Formal delimiters are not specified for separating user content from instructions. 3. Capability inventory: The skill does not define any capabilities for file manipulation, network communication, or code execution. 4. Sanitization: The process relies on manual quality verification rather than automated sanitization of inputs.
Audit Metadata