coherent-writing
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions and templates for text revision. It does not perform network operations, access sensitive files, or execute system commands. The workflow is entirely contained within the conversational context.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text drafts, which is a standard surface for indirect prompt injection. However, the risk is negligible as the skill's capabilities are limited to text editing and do not involve any dangerous tools or system access.
- Ingestion points: The skill ingests 'Draft text to revise' provided by the user (defined in SKILL.md).
- Boundary markers: There are no explicit instructions to use delimiters or to disregard instructions potentially embedded within the user's draft.
- Capability inventory: Analysis and revision of text. No access to subprocesses, shell, network, or filesystem.
- Sanitization: No input sanitization or validation is implemented.
Audit Metadata