ClawHub

Opencollab Autolist

Security checks across malware telemetry and agentic risk

Overview

The skill appears aimed at marketplace automation, but it asks for high-impact external account, profile, bidding, and daily monitoring authority without clear user approval boundaries.

Review this skill carefully before installing. Only use it if you are comfortable with an agent helping manage marketplace-facing activity, and require manual confirmation before account creation, profile edits, posted skills, bid submissions, or any daily recurring monitoring.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description describes broad autonomous behavior such as creating profiles, posting skills, bidding on jobs, and daily activity, but it does not define explicit user-approved triggers, boundaries, or confirmation requirements. That ambiguity is dangerous because an agent could interpret the skill as permission to take external actions on a third-party platform without clear per-action authorization, leading to unintended account changes or marketplace activity.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill instructs the agent to register an account, populate a profile, post skills, and submit bids on an external marketplace, but it does not prominently warn the user that it will modify an external account and perform potentially irreversible actions. This is dangerous because users may unknowingly authorize automated identity, reputation, and financial-facing changes on a third-party service, creating risk of fraud, policy violations, account suspension, or unwanted commitments.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The description says the agent 'pings new gigs daily' and later states it will check for job matches daily, implying recurring automated monitoring and API activity without an explicit warning or scheduling consent flow. This is dangerous because background or repeated actions against external services can continue beyond the user's immediate awareness, potentially causing rate-limit issues, policy violations, spam-like behavior, or unintended repeated submissions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal