Skillv1.0.0

VirusTotal security

gmailcleanerfall · External malware reputation and Code Insight signals for this exact artifact hash.

SuspiciousApr 30, 2026, 4:38 AM

Hash: d2ffc8484d63f5fc811001a9b3cb75c32e6ca92d189ff9137750a86249837275
Source: palm
Verdict: suspicious
Code Insight: Type: OpenClaw Skill Name: gmailcleanerv2 Version: 1.0.0 The skill bundle is designed for comprehensive email management, including reading, organizing, analyzing, and responding. It uses broad Gmail API scopes (read, modify, compose) and executes shell commands via `gog` CLI, often piped with `jq` and `xargs`. While these capabilities are necessary for its stated purpose, the broad API permissions and the use of `xargs` (even with controlled input like `.[].id`) present a vulnerability risk if the agent or its input were compromised. The `scheduler.py` script also includes an `--auto` flag that bypasses user confirmations for actions, which is a risky capability for automation. However, the `SKILL.md` files for `email-organizer` and `email-responder` explicitly instruct the agent to seek user confirmation for destructive or sending actions, and `email-analyzer/SKILL.md` even includes instructions for the agent to detect prompt injection patterns within emails. There is no clear evidence of intentional malicious behavior like unauthorized data exfiltration or hidden backdoors. The risks identified are primarily vulnerabilities that *could* be exploited, rather than proof of malicious intent, leading to a 'suspicious' classification.
External report: View on VirusTotal