research-lookup

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: Communicates with the Parallel AI API (api.parallel.ai) and OpenRouter (openrouter.ai) to process research queries and retrieve citations. These network operations are intrinsic to the skill's purpose and target established service providers.
  • [COMMAND_EXECUTION]: Executes included Python scripts via the Bash tool to perform data lookups and manage the local research archive in the sources/ directory. This is consistent with the skill's operational requirements.
  • [CREDENTIALS_UNSAFE]: Appropriately instructs the user to provide API keys via environment variables (PARALLEL_API_KEY and OPENROUTER_API_KEY), which is a standard and secure practice for managing secrets in development environments and avoids hardcoding sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — research-lookup