paper-search
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes text from external academic papers and search results (arXiv, PubMed, etc.), which represents a potential surface for indirect prompt injection if the external content contains malicious instructions designed to influence the agent.
- Ingestion points: Outputs from the 'paper-search search' and 'paper-search read' commands.
- Boundary markers: None specified in the instructions.
- Capability inventory: Shell command execution via the 'paper-search' CLI tool.
- Sanitization: Not explicitly described in the skill instructions.
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the 'paper-search-mcp' package via the 'uv' package manager to enable its functionality.
- [COMMAND_EXECUTION]: The skill relies on executing the 'paper-search' CLI tool to perform searches, download PDFs, and read paper content.
Audit Metadata