miro-browse
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize content from Miro boards, which are external, user-controllable data sources.
- Ingestion points: Data enters the agent context from Miro board URLs and item content fetched through Miro MCP tools as described in SKILL.md.
- Boundary markers: The instructions do not provide explicit delimiters or instructions to ignore potential commands embedded within the retrieved board content.
- Capability inventory: The skill enables the agent to list items, retrieve specific content, and access downloadable assets.
- Sanitization: There are no mentioned mechanisms for filtering or sanitizing the content retrieved from the board before the agent processes it for the user.
Audit Metadata