written-communication
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text providing mental models and writing frameworks for engineering managers. No executable code, scripts, or suspicious command patterns are present.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and articles hosted on the author's official newsletter domain (newsletter.manager.dev) to provide users with deeper context on the frameworks discussed.
- [COMMAND_EXECUTION]: The skill instructs the agent to read local context from the
.agents/directory (e.g.,em-context.mdand report files) to personalize its advice. This is standard behavior for maintaining context in an agentic environment and does not involve arbitrary command execution or shell access.
Audit Metadata