ljg-paper-flow
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected.
- [COMMAND_EXECUTION]: The skill invokes local tools 'ljg-paper' and 'ljg-card'. These are identified as vendor resources from 'lijigang' and represent intended workflow functionality.
- [PROMPT_INJECTION]: The skill processes external documents (papers and PDFs) which represents an indirect prompt injection surface.
- Ingestion points: Reads user-supplied arXiv links, paper URLs, and PDF files.
- Boundary markers: None identified in the workflow instructions.
- Capability inventory: Triggers tool execution ('ljg-paper', 'ljg-card') based on the content of these external sources.
- Sanitization: No explicit sanitization or filtering of external content is described before processing.
Audit Metadata