linkfox-zhihuiya-patent-forward-citation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCEEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes patent citation metadata and non-patent literature descriptions retrieved from the Zhihuiya API. This data represents an attack surface as it is ingested from an external source and displayed to the user.
- Ingestion points: Data is fetched via
zhihuiya_cited_references.pyfrom the/zhihuiya/patentForwardCitationAPI endpoint. - Boundary markers: The citation results are presented to the agent and user without explicit boundary markers or warnings regarding embedded instructions.
- Capability inventory: The skill can perform network operations (API calls) and write results to the local filesystem within the
linkfoxdirectory. - Sanitization: No specific filtering or sanitization of patent text for malicious instructions is performed prior to processing.
- [PERSISTENCE]: The
onboarding.mddocumentation instructs the agent to assist users in persisting theirLINKFOX_AGENT_API_KEYby adding export commands to shell profile files such as~/.zshrcand~/.bashrc. This is a legitimate mechanism for environment variable management across sessions. - [EXTERNAL_DOWNLOADS]: The
onboarding.pyscript and its documentation facilitate the installation and use of therequests,qrcode, andpillowlibraries for API communication and payment QR code generation.
Audit Metadata