openlibrary
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from openlibrary.org, which could theoretically contain malicious instructions designed to influence the agent.
- Ingestion points: External content enters the agent's context via the
openlibrary_org__get_searchtool and generic retrieval tools likeunbrowse.scrapeandunbrowse.mapdefined inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to wrap external content, making it harder for the agent to distinguish between valid data and embedded commands.
- Capability inventory: The skill provides search and cloud-based browser interaction capabilities (
unbrowse.browse.*) through the Unbrowse API. - Sanitization: There is no mention of sanitizing or validating the content returned from OpenLibrary before it is presented to the agent.
- [EXTERNAL_DOWNLOADS]: The skill connects to a remote MCP server and API endpoints hosted on the vendor's infrastructure (
unbrowse.ai). This connection is documented as the primary transport mechanism for the service's search functionality.
Audit Metadata