Wash-Trade-Detector

Detects and flags wash trades in NFT transaction data using 7 confidence-weighted patterns, protecting all downstream scoring and signals from artificial inf...

This skill appears internally consistent and low-risk from a permissions/installation standpoint, but review and testing are still important before production use: 1) Validate that all callers supply the required exact input fields and timestamp formats (timezones, ISO 8601) and that 'floor_price' is computed consistently. 2) Clarify ambiguous pattern language (e.g., Pattern 7's 'no other history') and edge cases (returns, legitimate repeat buyers) to reduce false positives. 3) Do not wire this skill to automatic exclusion without human review — consider logging flagged decisions and sampling for manual confirmation, especially for confirmed/excluded outcomes. 4) Ensure the calling pipeline enforces the stated guardrails (no DB writes or external reporting performed by the skill itself). 5) Test extensively on labeled historical data to measure false-positive/false-negative rates before using the output to block or exclude transactions.

Type: OpenClaw Skill Name: wash-trade-detector Version: 1.0.4 The OpenClaw skill 'Wash-Trade-Detector' is benign. Its `SKILL.md` clearly defines a specific task: detecting wash trades in NFT transaction data based on a set of weighted patterns. The instructions for the AI agent are consistent with this purpose, detailing input schema, detection logic, and output format. Crucially, the 'Guardrails' section explicitly prohibits actions such as 'pipeline writes, database access, and external integrations' and states the skill is 'Non-Destructive', actively preventing malicious behaviors like data exfiltration or unauthorized modifications. There are no signs of prompt injection attempts, obfuscation, or requests for sensitive system information.