drafting
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides pedagogical instructions and diagnostic frameworks for assisting writers. It does not perform network operations, access sensitive system files, or execute external code.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input and writes progress notes to local files (e.g.,
{project}-drafting-{date}.md). While it lacks explicit boundary markers for external data, it possesses no high-risk capabilities such as code execution, network exfiltration, or privilege escalation, rendering the attack surface benign.
Audit Metadata