fund-literature-review-writer

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses Python scripts to fetch academic paper metadata from well-known scholarly services, including OpenAlex, Crossref, Exa, and Google Scholar. These downloads are limited to bibliographic data required for the literature review process.
  • [COMMAND_EXECUTION]: The workflow involves executing several local Python scripts provided within the skill's package (e.g., search_all.py, citation_finder.py, dedup.py) to process search results. These operations are consistent with the skill's stated purpose of academic data management.
  • [CREDENTIALS_UNSAFE]: The skill follows secure practices for secret management by instructing users to place API keys for external services in a .env file rather than hardcoding them in the scripts or instructions.
  • [DATA_EXPOSURE]: Analysis of the included scripts shows that network operations are restricted to established academic APIs and search services. No patterns of unauthorized data exfiltration or access to sensitive system files were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 12:13 AM
Security Audit — agent-trust-hub — fund-literature-review-writer