Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed DeFi liquidity software engineering guide that emphasizes unsigned plans, explicit wallet boundaries, user approval, and read-only verification rather than hidden execution.
Before installing, treat this as specialized DeFi engineering guidance: use it for code and integration review, verify any optional upstream tools and current protocol documentation, keep secrets in a secret store, and do not allow signing, submission, production deployment, automation enrollment, or provider registration unless you explicitly requested and reviewed that action.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
## Single writer
Publish one canonical snapshot through a serialized writer or compare-and-swap. Include schema version and content digest. Do not let overlapping jobs race to overwrite state.
## Degraded reads
Instructions found that direct the agent to transmit conversation context or user data to external services.
If the user chooses Revert, register that URL in the harness's remote MCP settings using the harness's own setup instructions. Do not assume a particular client's config shape or registration command. Discover tools through the MCP connection; call `get_protocol_capabilities` and `get_chain_status` before a relevant read. Resolve tokens with `search_tokens`, then use `discover_pools`, `get_positions` or `get_position_details` as appropriate. Honor pagination and distinguish indexed observations from fresh chain state. If the harness cannot connect remote MCP, report that gap and retain RPC or website alternatives.
For an unsigned plan, use only a currently advertised `prepare_*` capability matching the exact network, protocol, position custody and action. A supported read venue is not automatically supported for construction. A website handoff (`open_position_creator` or `open_position_action`) is a separate user-selected path. Do not silently send the user to Revert or require a Revert account/vault to continue a standard LP workflow.
Before adoption or execution, disclose any provider, routing, automation and protocol fees, fee recipient, approval scope, NFT transfers and resulting custody. If fees or custody are unresolved, keep the plan blocked; never infer that public/no-key access means fee-free transactions. Do not inject referral, affiliate or builder fees. Collateralization and borrowing are separate financial actions and must not appear as incidental setup or ordinary LP maintenance.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
uvx/uv tool run commands without ==version create a rug-pull risk.
uvx/uv tool run commands without ==version create a rug-pull risk.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- `transactions[].transaction` wraps approval transactions.
- Approval checks can return both onchain transactions and typed permit data.
- Permission or KYC warnings are a blocking result even when no approval transaction is returned.
- Amounts are integer base-unit strings.
- Position ID and permit field names vary by endpoint.
- Tick-snapped adjusted prices are distinct from requested prices.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- [Uniswap AI skills](https://developers.uniswap.org/docs/uniswap-ai/skills)
- [Uniswap AI LP integration](https://github.com/Uniswap/uniswap-ai/tree/main/packages/plugins/uniswap-trading/skills/lp-integration)
- [Uniswap AI v4 SDK integration](https://github.com/Uniswap/uniswap-ai/blob/main/packages/plugins/uniswap-trading/skills/v4-sdk-integration/SKILL.md)
- [Uniswap LP API guide](https://developers.uniswap.org/docs/liquidity/liquidity-provisioning-api/integration-guide)
No suspicious patterns detected.