Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
A Stock Research
v1.0.0Comprehensive A-share (A 股) information gathering and analysis skills for Chinese stock market. Use when you need to query stock prices, analyze financial da...
⭐ 0· 41·0 current·0 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 (A-share research) aligns with the commands and listed 'installed' sub-skills (akshare-stock, china-stock-analysis, stock-watcher, stock-analysis). However, the SKILL.md repeatedly instructs the agent to run 'npx <package>' commands but the skill metadata declares no required binaries or install spec. If the agent is expected to run npx, that should be declared. The absence of declared required binaries (npx/node) is an incoherence.
Instruction Scope
Instructions are narrowly about querying and analyzing market data and managing watchlists, which fits the purpose. But they direct the agent to execute third-party npm packages at runtime (npx), which gives those packages freedom to run arbitrary code, access the filesystem, and contact external endpoints. The SKILL.md does not constrain or document where those packages come from or what network endpoints they use, so the agent could end up executing unexpected code.
Install Mechanism
There is no install specification in the skill bundle, yet the runtime examples use 'npx' to fetch and run packages. Relying on npx means fetching code from the npm registry (or a registry proxy) at runtime and executing it with the agent's privileges; this is a moderate-to-high risk unless the packages are audited and pinned. The skill does not declare or pin package sources, checksums, or versions, nor does it instruct to verify package provenance.
Credentials
The skill declares no required environment variables, credentials, or config paths and SKILL.md does not request any secrets. That is proportionate for a public-data research skill. (Note: dynamically-run npm packages could themselves request or use env vars when executed, which is not declared here.)
Persistence & Privilege
always:false and no install or code files means the skill does not request permanent elevated presence or modification of other skills. The skill lists a workspace path in documentation, but there is no declared behavior that writes or alters global settings.
What to consider before installing
This skill appears to be a coherent A-share research helper, but it relies on running npm packages at runtime via 'npx' while declaring no install requirements. Before installing or running: 1) confirm whether your agent environment has node/npx and whether you are comfortable with npx fetching and executing code from npm; 2) verify the exact npm packages/versions the skill will run (pin versions), inspect their source code or README, and ensure they come from trusted publishers; 3) run them in a sandboxed environment first (no access to sensitive files or credentials); 4) if you cannot audit the packages, avoid executing npx commands with elevated privileges or in an environment containing secrets. If the maintainer can provide a concrete install spec (pinned packages, checksums, or a vetted bundle), the risk would be lower.Like a lobster shell, security has layers — review code before you run it.
latestvk977xnh9tq44hf10vj0assza5s83zf37
License
MIT-0
Free to use, modify, and redistribute. No attribution required.