lp-integration
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external plugins and libraries, including the
@uniswap/uniswap-viemplugin and various Uniswap SDKs (@uniswap/sdk-core,@uniswap/v3-sdk, etc.). These are official resources from a well-known service (Uniswap) required for the stated purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as Ethereum addresses, token amounts, and chain IDs to construct API requests and generated code. It mitigates this risk through a mandatory 'Input Validation Rules' section that requires regex validation for addresses/amounts and explicitly rejects shell metacharacters.
- Ingestion points: User-provided parameters in
SKILL.mdfor constructing API requests. - Boundary markers: Explicit regex-based validation rules and shell character rejection.
- Capability inventory: Transaction building and API interaction via
fetchandcurl. - Sanitization: Hardcoded validation logic within the instructions.
- [COMMAND_EXECUTION]: Documentation includes examples of using
npmandcurlto interact with the Uniswap LP API and manage dependencies, which is standard for a development-focused integration skill.
Audit Metadata