SushiSwap API
Analysis
Prompt-injection indicators were detected in the submitted artifacts (base64-block); human review is required before treating this skill as clean.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Swap endpoints return **executable transaction data** - `tx.to` - `tx.data` - `tx.value` - `tx.gas`
The skill can help construct executable blockchain transaction data. This is central to the stated purpose and no signing authority is requested, but the output can affect user funds if later submitted.
The SushiSwap API supports customized integrator fees on swap-related endpoints ... Swap-related requests follow an **80/20 fee split by default**
The artifacts disclose referrer and fee behavior for swap-related requests. This is purpose-aligned but affects the economics of a swap.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Base URL ``` https://api.sushi.com ```
The skill is designed to send requests to an external SushiSwap API. Swap requests described in the schema include parameters such as sender, recipient, tokens, and amount.
