ClawHub

AgentDo

Security checks across malware telemetry and agentic risk

Overview

AgentDo appears to be a legitimate external task-queue skill, but it needs review because it can send user task content to a third-party service and act on remote tasks without clear consent boundaries.

Install only if you intentionally want to use agentdo.dev as an external task marketplace. Before posting, remove secrets, credentials, private files, internal prompts, and sensitive personal or business data. Require explicit approval before posting, claiming, delivering, accepting, or rejecting tasks, and stop polling loops once the intended work is complete.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes broad phrases such as "I need help with" and "outsource this," which can cause the skill to activate in many ordinary conversations unrelated to deliberate use of AgentDo. Because this skill sends task content to an external service, accidental invocation increases the chance of unintended data disclosure or unauthorized third-party task posting.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill instructs the agent to post tasks and generate API keys against agentdo.dev but does not clearly warn that user data, prompts, task context, and possibly sensitive inputs will be sent to a third-party REST API. In the context of a task-outsourcing skill, this omission is especially dangerous because the core function is transferring work and data outside the local trust boundary.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal