Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
CoinMarketCap MCP Skill
v1.0.0Use CoinMarketCap MCP through UXC for crypto market quotes, technical analysis, on-chain metrics, global market overview, narratives, macro events, news, and...
⭐ 0· 112·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's stated purpose (querying CoinMarketCap MCP via uxc) matches the instructions: all commands target the MCP endpoint and use uxc/coinmarketcap-mcp-cli. However, the SKILL.md requires a CoinMarketCap MCP API key and optionally references secret manager paths (op://...), but the registry metadata lists no required env vars or primary credential. That's an inconsistency between purpose and declared requirements.
Instruction Scope
The runtime instructions stay focused on discovery and read-only queries to the MCP endpoint and on configuring uxc auth bindings. They do not instruct reading arbitrary system files or exfiltrating unrelated data. The only notable scope issue is guidance to bind secrets (via --secret-env or secret-op) which implies access to environment variables or a secret store — reasonable for this API but not declared in metadata.
Install Mechanism
This is an instruction-only skill with no install spec, so nothing is written to disk or downloaded by the skill itself. That reduces install risk.
Credentials
SKILL.md expects an API key (COINMARKETCAP_MCP_API_KEY) and suggests optionally pulling a secret from an op:// path, but the skill metadata lists no required env vars or primary credential. Additionally, the included validate.sh script requires the 'rg' command and references local skill paths, but metadata lists no required binaries. The skill therefore asks for secret access in practice but does not declare that requirement in the registry metadata — this mismatch is concerning because users may not realize they must provide sensitive credentials.
Persistence & Privilege
The skill is not marked always:true and does not request system-wide configuration changes. It documents creating uxc auth bindings and a link command, which is normal for a connector. Autonomous invocation is allowed (default) but not combined with other red flags here.
What to consider before installing
This skill appears to legitimately wrap CoinMarketCap MCP via the uxc tool, but the SKILL.md requires a CoinMarketCap API key (COINMARKETCAP_MCP_API_KEY) and expects the uxc CLI to be present; the registry metadata does not declare those requirements. Before installing or enabling the skill: 1) Confirm you are willing to provide a CoinMarketCap MCP API key and understand where it will be stored (environment variable or your secret manager). 2) Ensure the 'uxc' tool exists and you trust its configuration and the 'uxc auth' bindings it will create. 3) Be aware the skill can be invoked autonomously by the agent (default); if you want to restrict that, adjust invocation permissions. 4) If you need stronger assurance, ask the maintainer to update registry metadata to declare the required env var (COINMARKETCAP_MCP_API_KEY) and any required binaries (e.g., uxc, and optionally rg for validation), and to explain how secret-op paths (op://...) are used and whether the skill attempts any network calls beyond mcp.coinmarketcap.com.Like a lobster shell, security has layers — review code before you run it.
latestvk97aaw6f91969fatcg5g9pzc35833d94
License
MIT-0
Free to use, modify, and redistribute. No attribution required.