aeon-defi-overview
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external DeFi market APIs to generate regime verdicts and yield sustainability reports, creating a potential vector for indirect prompt injection.
- Ingestion points: Data is retrieved from external services including DefiLlama (
api.llama.fi), GeckoTerminal, and various perpetual swap aggregators. - Boundary markers: The skill instructions lack explicit boundary markers or directives to ignore potential natural language instructions embedded within the fetched API data.
- Capability inventory: The skill's primary capabilities are analytical, focusing on reporting, regime classification, and yield decomposition.
- Sanitization: No specific evidence of data sanitization, filtering, or validation is present in the skill definition to mitigate malicious payloads in API responses.
- [EXTERNAL_DOWNLOADS]: The skill relies on external public data sources to function.
- The skill is configured to fetch real-time market data from DefiLlama, GeckoTerminal, and perp aggregators to compute TVL changes, volume, and funding rates.
Audit Metadata