@2061/yield-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or unauthorized access patterns were detected. The skill provides transparent functionality for DeFi yield optimization.
  • [EXTERNAL_DOWNLOADS]: The skill fetches yield data from DeFi Llama (yields.llama.fi) and the Pendle Finance SDK (api-v2.pendle.finance). These are well-known technology services and are considered trusted sources for financial data in this context.
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/scan_pools.py which is used for data aggregation and ranking. The script's logic is self-contained and limited to processing financial statistics.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data to drive actions. 1. Ingestion points: External yield data from the DeFi Llama API ingested by scripts/scan_pools.py. 2. Boundary markers: Absent as the data is treated as structured JSON for calculation. 3. Capability inventory: Capability to execute on-chain transactions through integration with the wallet skill. 4. Sanitization: Employs strict numeric filtering based on TVL thresholds and fixed risk-tier assignments to prevent manipulation from low-liquidity or malicious pools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 03:11 AM
Security Audit — agent-trust-hub — @2061/yield-optimizer