Social Media Scheduler
Analysis
This appears to be a local-only social media drafting and planning skill, with no evidence of posting, credential use, network access, or hidden code.
Findings (2)
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.
On first message, create data directory: `mkdir -p ~/.openclaw/social-media-scheduler`
The skill instructs a local shell command on first use. The command is simple and scoped to creating the skill's own directory, but users should notice that shell execution is requested.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
All data stored under `~/.openclaw/social-media-scheduler/`: `settings.json`, `calendar.json`, `ideas.json`, `drafts.json`
The skill persists brand details, content plans, ideas, and saved drafts for future use. This is purpose-aligned, but it creates reusable local context.
