Uniswap Find Yield
Analysis
This is a coherent instruction-only Uniswap yield-ranking skill, with only minor review notes about its reliance on another agent and an unpinned GitHub install example.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
npx skills add https://github.com/wpank/Agentic-Uniswap/tree/main/.ai/skills/find-yield
The installation example points to a GitHub main-branch path rather than a pinned release or commit. This is user-directed installation documentation, not hidden execution, but it is less reproducible.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
allowed-tools: [Task(subagent_type:opportunity-scanner)]
The skill delegates yield scanning to another named agent. This is purpose-aligned, but users should understand that the result depends on that subagent’s behavior and data handling.
