birdeye-plugin
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads its runtime components and version metadata from the official GitHub repository of the OKX organization. These downloads include integrity verification using SHA256 checksums before installation.
- [DATA_EXFILTRATION]: Implements robust protection against credential exposure by isolating Solana private key handling within a separate host process and providing explicit instructions to deny the agent direct read access to the key file.
- [COMMAND_EXECUTION]: Uses standard shell commands for the specific purpose of skill installation, environment verification, and update checking. The commands do not exhibit signs of arbitrary execution or malicious intent.
- [PROMPT_INJECTION]: Effectively mitigates indirect prompt injection risks by sanitizing and filtering all API response data through a whitelist of safe fields before surfacing information to the agent.
Audit Metadata