ChainaAware Behavioral Prediction

PassAudited by ClawScan on May 1, 2026.

Overview

The skill is coherently focused on ChainAware wallet and token risk analysis, but users should notice that it uses a ChainAware API key and sends blockchain identifiers to an external MCP endpoint.

This appears safe to install if you intend to use ChainAware’s external Web3 risk-analysis service. Before installing, make sure you are comfortable providing a ChainAware API key and sending queried wallet or contract identifiers to ChainAware; treat prediction scores as advisory, especially for lending, compliance, onboarding, or investment decisions.

Findings (3)

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.

What this means

Your ChainAware API key may be used whenever the agent invokes this skill for wallet or contract analysis.

Why it was flagged

The skill requires a ChainAware API key for service access. This is expected for a paid/external API integration, but users should understand they are delegating use of that credential to tool calls.

Skill content
requires:\n      env:\n        - CHAINAWARE_API_KEY\n    primaryEnv: CHAINAWARE_API_KEY
Recommendation

Use a dedicated, least-privileged ChainAware key if available, monitor usage, and revoke or rotate it if you uninstall the skill.

What this means

Blockchain identifiers you ask about may be transmitted to ChainAware, which could reveal what wallets, contracts, or tokens you are investigating.

Why it was flagged

The skill uses an external MCP endpoint and discloses that wallet, contract, LP, and network identifiers are sent to ChainAware for analysis.

Skill content
external_endpoints:\n        - url: https://prediction.mcp.chainaware.ai/sse\n          transport: SSE\n          purpose: Blockchain wallet and contract behavioural analysis\n          data_sent:\n            - Wallet addresses ...\n            - Smart contract / LP addresses\n            - Network identifier
Recommendation

Avoid submitting addresses you consider sensitive unless you are comfortable with ChainAware processing them under its privacy policy.

What this means

Users or agents may over-weight the prediction as definitive when making lending, listing, onboarding, or safety decisions.

Why it was flagged

The skill makes strong predictive-accuracy and future-behavior claims in a domain that can affect financial, onboarding, and compliance decisions.

Skill content
Fraud Detection — predict fraudulent wallet behavior before it happens (~98% accuracy on ETH) ... predictive — it tells your agent what is about to happen.
Recommendation

Treat the results as one risk signal and corroborate high-impact decisions with additional evidence and human review.