CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Security

2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.

Medium

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

Potentially malicious external URL detected (high risk: 1.00). The skill's "Fresh Context Policy" and playbook instructions explicitly require fetching live documentation at runtime (e.g., https://developers.jup.ag/... such as https://developers.jup.ag/docs/swap/index.md and the OpenAPI docs under https://developers.jup.ag/docs/openapi-spec/...), so those external docs are fetched at runtime and are treated as the authoritative source that directly controls agent behavior and instructions.

Report incorrect finding
Medium

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

Direct money access detected (high risk: 1.00). The skill is explicitly a Jupiter (DeFi/crypto) API integration and includes concrete, goal-directed transaction endpoints and flows for moving value: swap order/execute (/swap/v2/order, POST /swap/v2/execute), send (/send/v1/craft-send), lend deposit/withdraw endpoints (POST /lend/v1/earn/deposit etc.), recurring create/execute, trigger/limit-order create+execute (with JWT auth + signed deposit/cancel transactions), prediction market orders, and sample code to sign and send VersionedTransaction on Solana. These are explicit crypto financial execution capabilities (wallet signing + submitting on-chain transactions and REST endpoints that perform swaps/transfers/deposits), not generic tooling. Therefore it grants Direct Financial Execution Authority.

Repository
jup-ag/agent-skills
Audited
Security analysis
Snyk

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.