chainlink-ccip-skill
Handles Chainlink CCIP requests and never signs or broadcasts. It sends one-node GET diagnosis to chainlink-nop-skill. It sends ACE policy design to chainlink-ace-skill. Pool and message mechanics stay here. It applies to route, token, message-status, and lane lookups, fee estimates, cross-chain transfers and messaging, sender and receiver contracts, extraArgs V3, Fast Transfers, CCT token pools, and CCIP monitoring.
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./chainlink-ccip-skill/SKILL.mdW009: 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
Decisive operation: the skill prepares direct cross-chain transfers and token sends (no-contract CCIP sends/bridges via CLI, API, or SDK, plus Solidity sender/token-transfer work). It supplies unsigned or user-run transaction instructions for downstream execution, so it is in financial scope rather than an exclusion. Testnet limits do not remove scope, because the text does not establish fake funds or non-settling execution. The operation is direct, not indirect. Access-control gap: the only gates are agent-followed instructions (confirmation/"send mode" before token sends, the mandatory closing sentence, and the mainnet refusal). Wallet signing stays with the user, and the skill states it never signs or broadcasts. No service or execution-layer authentication or authorization enforces the route, so no qualifying independent control is established. Per the direct-operation rule, this is High.
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
The required monitoring and search workflow reads the CCIP API's `GET /v2/messages` results, where anyone can send a message with arbitrary `data` and token metadata to a monitored receiver, so outsider-authored text lands in a feed the agent queries without selecting a specific item.
- Repository
smartcontractkit/chainlink-agent-skills
- Revision
1d410d1
- 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.