miro-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill documentation and code samples align with the stated purpose of managing Miro connectors and items. It uses standard Node.js modules and API fetch patterns without any detected malicious intent or obfuscation.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests data from the Miro API and possesses write capabilities back to the platform.
  • Ingestion points: API responses from api.miro.com processed via miroFetch in SKILL.md.
  • Boundary markers: None identified in the provided code snippets or instructions.
  • Capability inventory: Network requests via miroFetch and local file reading via fs.readFileSync in SKILL.md.
  • Sanitization: No explicit sanitization or validation of API responses is demonstrated.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-core-workflow-b