mathworks
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites, creating a vulnerability surface where instructions embedded in those pages could be followed by the agent.
- Ingestion points: The mathworks_com__read_page tool in SKILL.md retrieves text and links from mathworks.com.
- Boundary markers: There are no explicit instructions or delimiters provided to separate or ignore instructions within the fetched data.
- Capability inventory: The skill includes capabilities to execute tasks and interact with pages via unbrowse.run and unbrowse.browse.act as described in SKILL.md.
- Sanitization: No data sanitization or validation processes are specified for the external content.
- [EXTERNAL_DOWNLOADS]: The skill connects to a remote MCP server provided by the vendor.
- Evidence: The skill connects to https://unbrowse.ai/mcp/mathworks.com as specified in server.json and README.md.
Audit Metadata