rubygems
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a remote Model Context Protocol (MCP) server hosted at
https://unbrowse.ai/mcp/rubygems.org. This endpoint is used to stream tool definitions and execute search operations on rubygems.org. This is a vendor-owned resource consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external search results.
- Ingestion points: Search result data, including titles, descriptions, and links retrieved from rubygems.org (SKILL.md).
- Boundary markers: There are no specific delimiters or instructional warnings in the skill's instructions to help the agent distinguish between data and commands within the retrieved search content.
- Capability inventory: The skill is scoped to remote API interactions with the Unbrowse platform; it does not contain commands for local file system access or subprocess execution.
- Sanitization: No sanitization or validation steps are defined for the data returned by the search tools before it is presented to the agent.
Audit Metadata