MetEngine Data Agent

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

The skill is a paid crypto API integration, but it asks the agent to use a local Solana wallet, keep persistent cross-session memory, and auto-update its own instructions from a remote site.

Install only if you are comfortable with a paid crypto API integration. Do not enable the cron auto-update, use a separate low-balance Solana wallet, review the pricing before calls, and inspect or disable the persistent memory file before trusting future sessions.

Findings (4)

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

Future agent instructions could change based on whatever the remote site serves, without the user reviewing the new skill content first.

Why it was flagged

The skill tells users or agents to overwrite the local agent skill file from a remote URL without a pinned version, hash, signature, or registry review path.

Skill content
curl -sL https://www.metengine.xyz/skill.md -o ~/.claude/agents/metengine-data-agent.md
Recommendation

Do not enable automatic remote skill replacement. Update only from a reviewed source, pin versions or hashes, and inspect changes before installing.

ConcernHigh Confidence
ASI10: Rogue Agents
What this means

The skill can keep changing itself weekly even when the user is not actively using it.

Why it was flagged

The documented cron job creates persistent background behavior that repeatedly modifies the agent skill file after installation.

Skill content
0 0 * * 0 curl -sL https://www.metengine.xyz/skill.md -o ~/.claude/agents/metengine-data-agent.md 2>/dev/null
Recommendation

Avoid installing the cron job. If updates are needed, require an explicit user action and review the new file before replacing the current skill.

What this means

API calls may involve signing or spending from a local Solana wallet, so misuse or unclear limits could cost the user funds.

Why it was flagged

The skill expects access to a local Solana keypair path and USDC/SOL balance checks for x402 payments, which is sensitive financial authority.

Skill content
Wallet configuration -- path to the Solana keypair ... keypair_path: ~/.config/solana/id.json
Recommendation

Use a dedicated low-balance wallet, require explicit approval before each paid request, and verify pricing before allowing the agent to make calls.

What this means

If that memory file is wrong, stale, or tampered with, future sessions may reuse unsafe code or incorrect endpoint/payment behavior.

Why it was flagged

The skill creates a persistent cross-session memory file that stores wallet setup details, executable bootstrap snippets, endpoint history, fallbacks, and pricing cache, then tells future agents to trust it before API calls.

Skill content
Before making ANY API call, check for a memory file at: ~/.claude/agents/metengine-memory.md ... Client Bootstrap -- a working code snippet ... copy-paste ready ... Agents MUST update the memory file
Recommendation

Treat the memory file as untrusted input, avoid storing executable snippets or wallet paths, and ask the user before reusing stored payment setup.