@2061/yield-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a Python script (scripts/scan_pools.py) for scanning and reporting DeFi yields. The script performs data processing using the standard requests library and does not execute arbitrary shell commands or access sensitive files.
  • [EXTERNAL_DOWNLOADS]: The skill fetches real-time yield data from yields.llama.fi and Pendle Finance's API. These are well-known and trusted services within the cryptocurrency ecosystem, and the references are documented neutrally.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from the DeFi Llama API at https://yields.llama.fi/pools (ingestion point). While it lacks explicit boundary markers for prompt interpolation, it has the capability to trigger transactions via the wallet skill (capability inventory). However, the skill implements sanitization by strictly filtering ingested data against a hardcoded whitelist of supported protocols and chains (sanitization).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:28 AM