aruba-it
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from the aruba.it website, which introduces a potential surface for indirect prompt injection. A third party could theoretically place malicious instructions on the target site to influence the agent's behavior.
- Ingestion points: Data enters the agent's context via the
aruba_it__get_enandaruba_it__read_pagetools described inSKILL.md. - Boundary markers: The instructions do not explicitly define delimiters or 'ignore' instructions for the agent when processing the retrieved web content.
- Capability inventory: The skill allows for page reading, link navigation, and automated login assistance ('autofill') as specified in the tools section.
- Sanitization: There is no specific documentation regarding the sanitization or filtering of the retrieved HTML or text content.
- [EXTERNAL_DOWNLOADS]: The skill is configured to connect to a remote tool provider at
https://unbrowse.ai/mcp/aruba.it. This connection is used to dynamically fetch and execute tool definitions for interacting with the targeted website.
Audit Metadata