scholar-search

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes specialized CLI tools (s2cli, openalexcli, arxivy, and dblpcli) to perform academic research tasks such as keyword searches and metadata retrieval.
  • [EXTERNAL_DOWNLOADS]: Utilizes the uvx runner to download and execute Python packages from the official Python Package Index (PyPI). These packages are part of the academic search infrastructure described in the skill's documentation.
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of academic paper metadata (titles, abstracts, and author names). This represents an indirect prompt injection surface. * Ingestion points: Academic metadata retrieved from Semantic Scholar, OpenAlex, arXiv, and DBLP. * Boundary markers: The skill encourages the use of structured JSON output (--json) which helps isolate data from instructions. * Capability inventory: Subprocess execution is restricted to the research tools; file system access is limited to writing bibliography files (e.g., .bib). * Sanitization: Relies on the provided CLI tools and the agent's internal safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 05:36 PM
Security Audit — agent-trust-hub — scholar-search