scholar-sidekick-api

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to interact with the Scholar Sidekick REST API (scholar-sidekick.com) to resolve scholarly identifiers like DOIs and PMIDs. All operations use standard curl commands to well-documented endpoints.
  • [EXTERNAL_DOWNLOADS]: The skill mentions an optional MCP server that can be run via npx -y scholar-sidekick-mcp@latest. This is a standard package from a scholarly tool provider and is presented as an alternative to the REST API calls. Documentation of this tool is transparent and contextually appropriate.
  • [COMMAND_EXECUTION]: The use of curl is restricted to interacting with the designated API (https://scholar-sidekick.com/api/*). There are no patterns of piping remote content to a shell or executing untrusted scripts.
  • [CREDENTIALS_UNSAFE]: The instructions correctly advise users on how to handle API keys, suggesting environment variables or Bearer tokens for higher rate limits, which aligns with standard security best practices for API integration. No hardcoded secrets are present.
  • [PROMPT_INJECTION]: The instructions do not contain any attempt to bypass LLM safety filters or override system instructions. It focuses purely on guiding the agent to use the API correctly.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 11:38 PM
Security Audit — agent-trust-hub — scholar-sidekick-api