integrating-jupiter
Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.
76
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill is explicitly a DeFi/crypto integration (Jupiter) that includes endpoints and code for executing on-chain financial operations: swap order/execute endpoints, lending deposit/withdraw endpoints, recurring order create/execute, trigger (limit order) create/confirm flows, send/craft-send and craft-clawback, plus a signAndSend helper that signs and sends VersionedTransactions with a wallet Keypair. These are specific blockchain transaction and fund-movement APIs (swap/execute, send, deposit, orders) — not generic tools — and therefore grant direct financial execution capability.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill's "Fresh Context Policy" and playbook instructions explicitly require fetching external documentation/OpenAPI specs at runtime (e.g., https://developers.jup.ag/docs/llms.txt and https://developers.jup.ag/docs/openapi-spec/swap/v2/swap.yaml), which would let remote content directly control the agent's behavior and decisioning.
- Repository
- jup-ag/agent-skills
- Commit
a2211e3
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.