AI News Briefing
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill appears coherent and purpose-aligned for generating AI news briefings, with no evidence of credential use, persistence, exfiltration, or destructive actions.
Before installing, make sure you trust the summarize and browser-execution skills it relies on. The reviewed artifacts otherwise describe a scoped, user-invoked workflow for summarizing public AI news sources.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
When invoked, the agent may browse the listed public news websites and send extracted snippets to a summarization model to produce the briefing.
The skill instructs the agent to use browser and summarization tools through a shell-style workflow. This is expected for a news briefing skill and is scoped to public AI news sources, but users should notice that it depends on broad browsing/summarization tools.
content=$(browser-execution "$source" 2>/dev/null) ... summary=$(echo "$ai_content" | summarize --model google/gemini-3-flash-preview)
Use it for the intended news-briefing task, keep source changes user-approved, and review the generated output rather than treating fetched web content as authoritative.
Installing or using this skill may require trusting the separate summarize and browser-execution skills.
The instruction-only package delegates its main behavior to other OpenClaw skills. This dependency is disclosed and purpose-aligned, but the overall safety of the workflow depends on the installed versions and permissions of those skills.
"dependencies": ["summarize", "browser-execution"]
Review and install trusted versions of the dependent skills before relying on this workflow.