skills/tw93/waza/write/Gen Agent Trust Hub

write

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (gh release view) to retrieve release data for style and content reference. This is a legitimate tool use within the context of generating project-specific release notes and social media copy.
  • [EXTERNAL_DOWNLOADS]: Fetches external content from GitHub repositories via the CLI to serve as templates or references for writing tasks. This interaction is limited to a trusted platform (GitHub) and is initiated based on user-provided repository identifiers.
  • [PROMPT_INJECTION]: The skill includes instructions for 'Document Review Mode' that act as safety guardrails, directing the agent to perform a privacy scan and halt processing if PII, competitor information, or other sensitive data is detected in the input text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 05:25 PM
Security Audit — agent-trust-hub — write