keyapi-twitter

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Node.js scripts to automate the configuration of environment variables and the execution of REST API calls. The configure-keyapi-auth.mjs script modifies shell configuration files (such as .bashrc, .zshrc, and PowerShell profiles) to store the KEYAPI_TOKEN for persistence across sessions.
  • [DATA_EXFILTRATION]: The skill transmits API tokens and request data to the vendor's official endpoint at https://api.keyapi.ai. This is the intended behavior for the service and is used to retrieve Twitter/X content.
  • [SAFE]: The skill demonstrates security awareness by instructing the agent never to print or restate the KEYAPI_TOKEN. All external URLs and resources belong to the verified vendor domain keyapi.ai. The scripts rely on Node.js built-in modules, avoiding third-party dependency risks.
  • [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface as it ingests untrusted content from Twitter/X. It mitigates this by providing clear instructions to the agent to separate observed API facts from inference and to follow analytical reporting rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 09:25 AM
Security Audit — agent-trust-hub — keyapi-twitter