Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed DeFi liquidity-planning helper that produces unsigned plans and review links, not signatures or submitted transactions.
Use this skill only for planning and review. Before acting on any output, verify the pool, chain, tokens, approval scope, spender, fees, slippage, deadline, calldata, provider, and final wallet display; do not treat a generated URL or unsigned transaction as safe to sign without independent review.
Referenced artifact was not completely inspected
the choice, apply [backtesting standards](references/backtesting.md). Use `node scripts/range.mjs --help` for deterministic tick snapping. Treat its output as a
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.
The description lists a wide range of common user asks such as position size, token amounts, approvals, slippage limits, deadlines, transaction order, and preflight checks as reasons to use the skill. While domain-related, it does not define concrete trigger phrases, exclusion examples beyond a few high-level negatives, or clear boundaries for when another skill should handle the request, which could lead to unintended invocation for generic DeFi planning questions.
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.
For a chosen verified pool, first produce a field-complete draft showing known and missing identity, user budget, range and spend limits. Use the local range script only after token orientation and tick spacing are known. Missing quotes or simulation make the plan explicitly non-executable.
Receive analysis evidence or equivalent independently verified identity, risk and exit evidence. Return chain/wallet/pool identity, observation block, exact amounts/ticks, maximum spends, approval terms, targets/calldata/value, expected effects, simulation evidence, deadline and missing fields to `lp-execute`. Related skills are optional: if analysis is absent, verify identity, token behavior, hook/gauge risk and exit feasibility through trusted reads; if these cannot be established, retain a non-executable draft. If execution is absent, return the unsigned plan without asking for a signature.
Resolve script and reference paths from this installed skill directory, not the agent workspace. Discover related skills by exact name in the harness; do not assume a sibling directory or silently install another skill. For missing RPC, ABI, quote or wallet capabilities, use `lp-setup` if available, otherwise inventory actual tools and report the missing method. Instructions alone do not supply live data or execution integrations.
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.
Bind chain, wallet, Sickle address and owner, any approved operator, factory, registry, strategy, connector, gauge, pool and output recipient. For a new account, show Sickle creation as an explicit plan effect. A wrapper that owns the Sickle and redirects rewards is a separate custody/fee choice; do not insert it to make an SDK example work.
Decompose any one-click route into approvals, input swaps, liquidity addition/removal, staking, reward processing and residue transfers. Show the input token, integer maximum spend, minimum outputs, slippage/price-impact guards, native value, approval scope, deadline and each target. UI convenience does not imply one signature, no approvals or one trust domain. Keep the draft non-executable if exact calls or independent simulation are missing.
## Charge the correct fee basis
The script constructs a live https://app.uniswap.org/positions/create?... URL that pre-populates transaction-relevant parameters for adding liquidity, which materially exceeds the skill’s declared planning-only scope. In this context, the gap is dangerous because downstream agents or users may treat the generated link as an endorsed execution artifact and move directly toward wallet interaction without a separate safety gate or reassessment.
The help text says 'Build a reviewed Uniswap position-creation link,' implying the script has performed substantive review. In reality, the implementation performs local format/range checks and string assembly, with no external verification of chain support, token order, fee validity, hook safety, or interface schema.
This code emits a ready-to-use Uniswap position-creation URL that can prefill deposit parameters, which could influence financial actions by the user. Although the help text includes a warning, the main execution path prints the link directly without any user-facing confirmation or disclosure at the point of use.
No suspicious patterns detected.