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.
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/integrating-jupiter/SKILL.mdSecurity
3 findings — 3 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). The SKILL.md's "Fresh Context Policy" explicitly directs the agent to fetch the playbook's linked refs (e.g., https://developers.jup.ag docs, linked OpenAPI specs, GitHub repos, and https://status.jup.ag), meaning the agent will ingest and act on public third-party web content that can change runtime behavior.
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: 0.90). The skill's "Fresh Context Policy" requires the agent to fetch external documentation at runtime and treat it as authoritative guidance (e.g., https://developers.jup.ag/docs/llms.txt), so remote content from developers.jup.ag would directly control agent instructions and is a required runtime dependency.
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 DeFi/crypto integration for Jupiter on Solana and provides concrete, specific APIs and code paths that perform monetary operations. It documents endpoints to create and execute swaps (GET /swap/v2/order -> sign -> POST /swap/v2/execute), lending deposit/withdraw (POST /lend/v1/earn/deposit, /withdraw), limit orders (POST /trigger/v2/orders/price with signing), recurring DCA create/execute (POST /recurring/v1/createOrder -> sign -> POST /recurring/v1/execute), prediction-market orders (POST /prediction/v1/orders), and token sends (POST /send/v1/craft-send). The quickstart includes a signAndSend helper that deserializes, signs, and broadcasts VersionedTransactions — i.e., signing and submitting on-chain value transfers. These are specific, purpose-built financial transaction endpoints and signing flows (not generic HTTP or browser automation), so the skill grants direct financial execution capability.
- Repository
- jup-ag/agent-skills
- Commit
b0a4830
- 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.