defi-protocol-interaction

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill ingests untrusted data from the DeFi Llama API in scripts/defi_tvl.py and from public blockchain RPC providers in scripts/aave_positions.py and scripts/uniswap_quote.py.
  • Boundary markers: No specific delimiters or instructions are used when the agent processes this external data.
  • Capability inventory: Analysis of all scripts confirms no use of subprocess, eval/exec, file-write operations, or other high-privilege capabilities.
  • Sanitization: The skill performs basic truncation of external descriptions but does not implement sanitization to prevent the interpretation of malicious instructions within the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 07:33 PM