Back to skill
Skillv1.0.0
VirusTotal security
Claude Delegate · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 29, 2026, 5:33 AM
- Hash
- d0871cde11340217a3e8b93354e1f1b3b0fd1e15b43d90ce94bb9ab33b5da931
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: claude-delegate Version: 1.0.0 The skill instructions in SKILL.md direct the agent to execute the Claude CLI using the `--permission-mode bypassPermissions` flag. This flag explicitly disables interactive safety prompts, allowing the delegated Claude process to perform arbitrary file modifications and command executions without user confirmation. While this is a legitimate feature for automation, recommending its use within an autonomous agent framework creates a high-risk environment where malicious or unintended actions could occur silently.
- External report
- View on VirusTotal