skills/whizzzkid/skills/wk-slack/Gen Agent Trust Hub

wk-slack

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses established Slack MCP tools for messaging and reading channel/user data. All tool use follows the principle of least privilege within the communication domain.
  • [SAFE]: The instructions emphasize safety by mandating a human-in-the-loop review process ('HARD RULE — always show the composed message to the user before posting').
  • [SAFE]: A privacy filter is explicitly defined for standup snippets to ensure that sensitive data like HR information, candidate PII, and personal communications are excluded from public channel posts.
  • [SAFE]: The skill documents standard web clipboard APIs (ClipboardItem) and provide fallbacks for older browser environments. No suspicious obfuscation or remote code execution patterns were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 09:50 PM
Security Audit — agent-trust-hub — wk-slack