jupiter
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Jupiter API (lite-api.jup.ag) and Solana RPC endpoints, creating a potential surface for indirect prompt injection.
- Ingestion points: External data enters via jupiter_swap, jupiter_price, and jupiter_limit_orders in exports.py.
- Boundary markers: The SKILL.md instructions explicitly require the agent to present all trade details to the user and obtain manual confirmation before proceeding to sign or broadcast transactions.
- Capability inventory: The skill uses jupiter_execute_swap and jupiter_broadcast_tx to interact with the Solana blockchain.
- Sanitization: Data from external APIs is formatted for display but does not undergo specific content filtering for natural language instructions.
- [DATA_EXPOSURE]: The _trade_report.py module transmits trade metadata (wallet addresses, symbols, and transaction hashes) to a vendor-controlled endpoint specified by the AI_AGENT_API_URL environment variable. This telemetry is an integrated feature of the skill authored by starchild-ai-agent and uses a platform-issued CONTAINER_JWT for authentication.
Audit Metadata