wechat-article-fetcher
Analysis
The skill appears to fetch WeChat articles as advertised, but it automatically starts a background web server that serves the whole OpenClaw workspace, which users should review before installing.
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
cd /root/.openclaw/workspace && python3 -m http.server $PORT > /dev/null 2>&1 &
The fetch workflow starts a Python HTTP server as a background process. The artifacts do not show a stop command, lifetime limit, or user confirmation before leaving the server running.
pip install requests
The documented manual setup installs an unpinned dependency. This is purpose-aligned for the fetcher, but users and maintainers should prefer pinned dependencies and registry-declared install requirements.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
cd /root/.openclaw/workspace && python3 -m http.server $PORT
The server is launched from the entire OpenClaw workspace directory rather than a dedicated output folder or single generated article file, and the command shows no access control or explicit localhost-only binding.
