ClawHub
Back to skill

Security audit

Ooze Agents

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for an external identity and reputation badge service, with privacy-relevant but disclosed API use.

Install this only if you want an Ooze Agents identity tied to verification and activity on supported platforms. Keep the Ooze API key private, prefer a secret store or environment variable over pasting real tokens into chats or logs, and require explicit approval before profile changes, guestbook posts, key rotation/revocation, or NFT minting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Low
Confidence
88% confidence
Finding
The skill explicitly instructs the agent to persist state in a local file (`memory/ooze-state.json`) even though the core purpose is an external badge/evolution service. Unnecessary local persistence increases data-retention and workspace-modification risk, especially if users are not informed or if multiple skills share the same storage area.

Vague Triggers

Medium
Confidence
94% confidence
Finding
Several triggers are broad, generic terms such as `creature`, `evolution`, `xp`, and `verification badge`, which can match ordinary conversation unrelated to this skill. That raises the likelihood of unintended activation, causing unsolicited network calls, state writes, or guidance tied to this external service.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill tells the agent to store persistent state in a local file without warning the user that local writes will occur. Silent persistence can violate user expectations, create privacy concerns, and leave behind residual data that later tools or users may access.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding
The trigger `xp` is extremely short and commonly used across gaming, reputation, and reward contexts, so it is highly prone to accidental matches. This can cause the skill to activate in unrelated conversations and increase the chance of unnecessary external interactions.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.