literature-search-openalex

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill implements secure API key management by instructing the user to store credentials in a local .env file. It explicitly prohibits the agent from reading or printing the contents of this file, preventing the leakage of sensitive keys into the conversation context.
  • [COMMAND_EXECUTION]: All operations are performed through a dedicated Python CLI utility. The skill uses uv to manage dependencies and run the script, avoiding arbitrary shell command execution and ensuring a controlled environment.
  • [DATA_EXFILTRATION]: Network activity is restricted to communicating with the OpenAlex API (api.openalex.org) and its content servers (content.openalex.org). The PDF download functionality includes magic-byte verification to ensure that only valid PDF files are retrieved, mitigating risks associated with fetching arbitrary remote content.
  • [SAFE]: The CLI utility includes logic to truncate large JSON outputs when displayed in a terminal. This prevents the agent's context from being flooded with excessive data, which could otherwise be used as a denial-of-service vector or to hide malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:50 PM
Security Audit — agent-trust-hub — literature-search-openalex