zoom-mcp/whiteboard
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Zoom Whiteboards, which could contain untrusted instructions intended to influence agent behavior.
- Ingestion points: Tools such as
get_a_whiteboardandlist_whiteboardsfetch content from the Zoom service (SKILL.md, references/tools.md). - Boundary markers: The instructions lack delimiters or warnings to ignore instructions embedded within the retrieved whiteboard content.
- Capability inventory: The skill includes tools for managing whiteboard collaborators, such as
add_a_whiteboard_collaboratoranddelete_a_whiteboard_collaborator, which could be abused if the agent is influenced by malicious content (SKILL.md, references/tools.md). - Sanitization: There are no guidelines provided for sanitizing or validating the content retrieved from whiteboards before it is processed by the agent.
Audit Metadata