Back to skill
Skillv1.0.0
VirusTotal security
Internal Comms Anthropic · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
ReviewApr 30, 2026, 6:19 AM
- Hash
- b1b5ede1ce493a6f22acef258735f40134c88822987ce81d9c8754efe53e5f23
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: internal-comms-anthropic Version: 1.0.0 The skill bundle instructs the AI agent to perform broad data aggregation across sensitive corporate platforms including Slack, Google Drive, Email, and Calendar (specifically in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md). While the stated goal is to facilitate internal communications, the instructions to search for high-engagement posts, executive emails, and 'critical' documents constitute a high-risk capability with an extremely broad permission scope. No evidence of exfiltration to external domains was found, but the potential for unauthorized data exposure or privacy violations via the agent's automated summaries is significant.
- External report
- View on VirusTotal