Uniswap Track Performance

Track the performance of Uniswap LP positions over time — check which positions need attention, are out of range, or have uncollected fees. Use when the user asks how their positions are doing.

This skill seems to do what it says, but it implicitly expects access to a configured wallet/private key even though it doesn't declare required environment variables. Before installing or using it: 1) Ask what the 'portfolio-analyst' subagent does and whether it requires a PRIVATE_KEY or will perform on-chain transactions. 2) Never paste or store your private key into a third-party skill; prefer providing a read-only wallet address for analysis, or use an RPC/subgraph API that only requires public data. 3) If the skill (or portfolio-analyst) requests env vars like PRIVATE_KEY, decline unless you fully trust the code and can audit it; prefer solutions that use a hardware wallet or read-only view keys. 4) If you plan to follow the README's npx/install commands, treat that as a separate trust decision — inspect the remote repo first. 5) Ask the skill author to explicitly list any required env vars and to confirm that analysis will be read-only (no private key transmission or transactions).

Type: OpenClaw Skill Name: track-performance Version: 0.1.0 The skill bundle is benign. Its primary function, as described in SKILL.md, is to delegate performance tracking of Uniswap LP positions entirely to a `portfolio-analyst` subagent, as explicitly stated in `allowed-tools: [Task(subagent_type:portfolio-analyst)]` and reinforced in the 'Important Notes'. There are no direct execution commands, file system access, network calls, or attempts at data exfiltration within this skill's definition. The SKILL.md instructions for the AI agent are clear, aligned with the stated purpose, and do not contain any prompt injection attempts to subvert the agent's behavior. Installation instructions in README.md are standard for the platform and point to the skill's own repository.