pp-open-library
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
open-library-pp-clitool usingnpxfrom the@mvanhornregistry andgo installfrom themvanhornGitHub repository. These resources are hosted on the vendor's official distribution channels. - [COMMAND_EXECUTION]: The skill relies on the
Bashtool to execute theopen-library-pp-clibinary for retrieving book, author, and edition metadata. - [PROMPT_INJECTION]: The skill retrieves and processes metadata from the Open Library API, creating a vector for indirect prompt injection.
- Ingestion points: Data returned by the
open-library-pp-clitool from Open Library (e.g., search results, author works, work metadata) as seen in the recipes inSKILL.md. - Boundary markers: The skill does not define clear boundaries or markers to isolate external data within the agent's context.
- Capability inventory: The agent is authorized to use the
Bashtool (defined in theallowed-toolsofSKILL.md), allowing it to execute local shell commands. - Sanitization: The skill lacks explicit instructions for sanitizing or validating the content received from the external API.
Audit Metadata