Csam Shield

• Analyzed: May 12, 2026, 4:29 AM
• Findings: 1
• Version: 1.0.0
• Hash: dfee21103813530249b50a7c6207bd0f44121a208bcafe2ffb0dbb3ef9724aaf
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill exhibits high-risk capabilities, including extensive file system access for content analysis, external network communication to `https://report.cybertip.org/` for NCMEC reporting, and the ability to suspend users and block IPs. The `SKILL.md` also contains instructions for the AI agent to suppress user notifications ('Do NOT notify user of detection'), which, while legally mandated for CSAM, represents a non-transparent action. These capabilities are plausibly needed for the stated purpose of CSAM detection and reporting, but their inherent power and the instruction for non-transparency classify the skill as suspicious rather than benign, as there is no clear evidence of intentional malicious behavior like unauthorized data exfiltration or backdoor installation.