birdeye
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [DYNAMIC_EXECUTION]: The
exports.pyscript utilizesimportlib.utilto dynamically load and execute functions from local files within thetools/directory for internal modularity.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external token data (e.g., names, symbols, security issues) from the Birdeye API. This untrusted content enters the agent's context without sanitization or boundary markers, creating a potential surface for indirect prompt injection.\n- [DATA_EXFILTRATION]: The skill communicates with the Birdeye API (public-api.birdeye.so) to fetch blockchain analytics data.
Audit Metadata