semantic-scholar-deep

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches academic paper metadata, citations, and recommendations from the official Semantic Scholar API (api.semanticscholar.org). All remote operations are directed to this legitimate service using Python's standard library.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (ss_client.py and citation_graph.py). These scripts are used for API interaction and graph traversal, and do not contain any arbitrary command execution or shell injection vulnerabilities.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill correctly manages API authentication via the SEMANTIC_SCHOLAR_API_KEY environment variable, avoiding hardcoded secrets. The subagent instructions include safety-conscious practices like explicit date-anchoring to ensure research accuracy.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 11:48 PM