paper-search

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'uv run' command to execute a local CLI tool named 'paper-search'. This execution is used to perform searches, downloads, and text extraction based on user input.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading academic papers from established and well-known services including arXiv, PubMed, Semantic Scholar, and CrossRef. These operations are core to the skill's academic research purpose.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted text content extracted from external academic papers.
  • Ingestion points: Extracted text from academic papers via the 'read' command output.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when presenting extracted text to the agent.
  • Capability inventory: The skill maintains capabilities for subprocess execution ('uv run'), network search operations, and local file writing ('download').
  • Sanitization: There is no indication of content validation or sanitization of the text retrieved from external sources before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 02:46 AM