miro-doc
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides benign natural language instructions for interacting with the Miro platform. No signs of data exfiltration, unauthorized command execution, or credential exposure were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes user-provided content to generate Miro board widgets.
- Ingestion points: User-provided content or topic generation strings (SKILL.md, Workflow step 2).
- Boundary markers: None identified.
- Capability inventory: Invocation of Miro MCP tools for document creation and modification.
- Sanitization: None identified within the skill instructions. This surface is inherent to the skill's primary function and does not represent an active security threat within the skill code itself.
Audit Metadata