miro-incident-runbook

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized behaviors were detected.- [CREDENTIALS_UNSAFE]: The skill demonstrates secure practices by explicitly instructing the agent to never print or expose Miro access tokens, refresh tokens, or client secrets.- [EXTERNAL_DOWNLOADS]: All external references are directed toward official Miro documentation and status pages (miro.com), which are recognized as trusted sources for this integration.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied incident symptoms and repository content. This attack surface is mitigated by requirements for read-only probes, UTC action logging, and mandatory incident commander approval for all mutations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-incident-runbook