technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides comprehensive guidelines for technical documentation, covering Diátaxis structures, Google developer style, Simplified Technical English (STE), and Global English rules. The instructions are entirely focused on linguistic and stylistic improvements for writing tasks like RFCs, READMEs, and commit messages.
- [SAFE]: The skill explicitly disables model invocation in its metadata (
disable-model-invocation: true), which restricts the agent's ability to trigger external tools autonomously, further reducing the attack surface. - [EXTERNAL_DOWNLOADS]: The
UPSTREAM.mdfile contains links to the source repository on GitHub (github.com/cursor/plugins). These references are used for documentation and version tracking of the vendored skill and target a well-known service.
Audit Metadata