Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Create Content

v1.0.0

Thinking partner that transforms ideas into platform-optimized content

6· 3.2k·16 current·16 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name and description match the SKILL.md: the skill is a thinking partner that helps turn ideas into platform-optimized posts. It requests no binaries, credentials, or installs that would be unexpected for this purpose.
Instruction Scope
Most instructions stay within content-creation scope (clarifying questions, voice guidelines, drafting for X/LinkedIn). One guidance item — 'Search for recent notes, journal entries, sessions' — asks the agent to access user-authored personal data but doesn't specify which sources, limits, or consent flows. That is plausible for a content helper, but the instruction is vague and could lead to broad or surprising data access if not constrained by the platform or user.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk write/exec risk.
Credentials
Requires no environment variables, credentials, or config paths. The skill does not request secrets or unrelated permissions.
Persistence & Privilege
always is false and no special privileges are requested. Model invocation is allowed (platform default) which is appropriate for an autonomous helper.
Assessment
This skill appears to do what it says: help refine ideas and draft posts for platforms like X and LinkedIn. Before installing, consider how the agent will implement the instruction to 'search for recent notes, journal entries, sessions' — ask the author or platform whether the agent will only use explicit data you provide or whether it will scan your personal notes/archives automatically. If automatic search is possible, ensure you understand and consent to which sources (e.g., specific local files, connected note apps) will be accessed. Otherwise the skill is low-risk and coherent with its purpose.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fyyzshjzxxyq7kqa44bm0kx7zvcf0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments