Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Pipeworx sec
v1.0.0Query the SEC EDGAR database to find companies, retrieve recent filings by form type, and access key financial metrics from XBRL data.
⭐ 0· 35·0 current·0 all-time
byBruce Gutman@brucegutman
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The declared capabilities (search companies, get filings, read XBRL facts) match the stated purpose and are reasonable for SEC data (which is public). However the SKILL.md does not say the skill will proxy requests through a third‑party service, so the external gateway is unexpected relative to the description.
Instruction Scope
The instructions explicitly show JSON-RPC calls to https://gateway.pipeworx.io/sec/mcp and include an mcpServers mapping. That directs the agent to send queries (and any supplied arguments) to a third‑party endpoint instead of directly to sec.gov. The doc does not describe what the gateway does, what it logs, or whether additional context will be forwarded — that creates a potential data‑exfiltration/privacy risk.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is written to disk or installed, which reduces risk.
Credentials
The skill requests no credentials, env vars, or config paths; that is proportionate for public SEC data. That said, absence of required credentials also means the gateway may accept unauthenticated traffic — the SKILL.md offers no transparency about who runs the gateway or how data is used.
Persistence & Privilege
always is false and the skill does not request elevated or persistent presence. Autonomous invocation is allowed by default but not combined with other privilege escalation indicators.
What to consider before installing
Before installing, confirm who operates https://gateway.pipeworx.io and whether requests and arguments you send (including any contextual prompt data) are logged, stored, or shared. If you only need public EDGAR data, prefer a skill that calls the SEC/EDGAR endpoints directly or that documents the proxy's privacy/security practices. Ask the publisher for an audit/trust statement or source code; avoid sending sensitive context or internal identifiers through this skill until you can verify the gateway's operator and retention policy.Like a lobster shell, security has layers — review code before you run it.
latestvk97bd89e03p4nx3qxxdv56h9bd84vh8f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.