ClawHub
Back to skill

Security audit

Deerflow

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed DeerFlow client that sends research prompts to a configured service, with no evidence of hidden installation, persistence, or destructive behavior.

Install only if you control or trust the DeerFlow endpoint, because research prompts will be sent there and may be processed by its model/search providers. Prefer explicit /deerflow invocation for sensitive topics, and review the separate DeerFlow Docker deployment before running it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrase `deep research` is broad and likely to appear in ordinary user conversation, which can cause accidental invocation of this skill. Because the skill submits user prompts to an external DeerFlow service, an unintended trigger could send sensitive or irrelevant user content off-box without clear intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.