content-writing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code or external dependencies. It is a set of markdown-based instructions for content creation and review.
- [SAFE]: No network operations, sensitive file access, persistence mechanisms, or obfuscation techniques were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to process and review user-provided text for articles, blog posts, and research. However, the skill lacks any dangerous capabilities such as network access, file system manipulation, or command execution that could be exploited by such an injection.
- Ingestion points: Processes user-supplied drafts, outlines, and research topics defined in the collaborative workflow (SKILL.md).
- Boundary markers: None present to distinguish user content from instructions.
- Capability inventory: No subprocess calls, network operations, or file-writing tools are utilized or requested.
- Sanitization: None present for external content.
Audit Metadata