lp-operate
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages liquidity operations by ingesting data from untrusted external sources such as token metadata, smart contract strings, and DeFi APIs.
- Ingestion points: Data enters the agent context through external websites, APIs, and blockchain metadata as described in
SKILL.md. - Boundary markers: The workflow includes an 'Authorization gate' and a 'Confirmation contract' requirement (
references/confirmation-contract.md) to prevent unauthorized execution. - Capability inventory: The skill utilizes wallet execution tools for financial transactions, including approvals and liquidity movements.
- Sanitization: Instructions require decoding all calldata and performing state reconciliation after every transaction (
references/transaction-state-machine.md). - [NO_CODE]: No executable code, scripts, or binaries are included with this skill; it is comprised entirely of markdown instructions and configuration files.
Audit Metadata