Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Content Ideas Generator
v1.0.0Generates structured post outlines from reference materials for wisdom-style social posts. Use when someone wants to extract compelling concepts from newsletters, scripts, notes, or other content and transform them into engaging post outlines with paradoxes, transformations, and powerful insights.
⭐ 1· 3k·8 current·8 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the runtime instructions: the SKILL.md describes extracting themes and producing five outlines. There are no unrelated credentials, binaries, or install steps requested that would contradict the stated purpose.
Instruction Scope
Instructions stay within the stated purpose: ask for reference material, analyze it, produce outlines, and save to content-ideas/ideas-{timestamp}.md. It may fetch content from user-supplied URLs using web_fetch (expected). It does not instruct reading system files, environment variables, or unrelated configs.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and arbitrary code execution risk.
Credentials
No environment variables, credentials, or config paths are required. The requested capabilities are proportional to the content-generation function.
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges. It writes its own output file under content-ideas/, which is consistent with its purpose.
Assessment
This skill is internally consistent with its description, but consider the following before installing: (1) The agent will fetch any URL you provide — avoid giving links to sensitive or private resources. (2) Generated outputs are saved to content-ideas/ideas-{timestamp}.md — confirm where your platform stores those files and who can access them. (3) The skill encourages absolute language and direct quoting; review outputs for factual accuracy, copyright issues, or unintended personal data before publishing. (4) Because it's instruction-only and can run autonomously by default, review agent invocation settings if you want to limit when the skill runs. If you need further checks (e.g., where files are stored on disk or platform-specific permissions), provide platform details and I can advise more specifically.Like a lobster shell, security has layers — review code before you run it.
latestvk9751whnr2k0nynqtvf6tzwdn58019ps
License
MIT-0
Free to use, modify, and redistribute. No attribution required.