paper-lookup

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates communication with 10 well-known academic and scientific repositories, including the National Center for Biotechnology Information (PubMed/PMC), arXiv, Crossref, Semantic Scholar, and OpenAlex to retrieve paper metadata and full-text content.
  • [COMMAND_EXECUTION]: Instructions specify the use of platform-specific web fetch tools or shell-based curl commands as a fallback to interact with legitimate REST API endpoints described in the reference documentation.
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of research paper abstracts and full-text articles; this represents an indirect prompt injection surface. However, the risk is mitigated by the reputable nature of the academic sources and the skill's intended purpose of scholarly search.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:48 AM
Security Audit — agent-trust-hub — paper-lookup