written-communication
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is entirely composed of Markdown documentation and templates. No executable scripts (Python, JavaScript, shell) or package manager configuration files (requirements.txt, package.json) are present.
- [DATA_EXPOSURE_AND_EXFILTRATION] (SAFE): No sensitive file paths, hardcoded credentials, or network operations were found. The skill specifically instructs the agent to ensure 'no secrets, credentials, or unnecessary sensitive/PII details' are included in the generated artifacts (CHECKLISTS.md).
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill is designed to ingest and process untrusted external data such as notes and Slack threads (SKILL.md). While it lacks boundary markers for this input, its capabilities are limited to internal text generation with no side effects like file writing or network access, presenting negligible risk.
Audit Metadata