Find Skills.Tmp

• Outcome: Review
• Latest audit: May 29, 2026 at 9:24 PM UTC
• Version:
  1.0.0

Overview

This skill appears intended for skill discovery, but its broad activation and global noninteractive install guidance could push users into persistent third-party installs without enough review.

Review carefully before installing. Use this only when you explicitly want help finding or installing external skills, and require the agent to show the package source, publisher, and exact command before any install. Prefer sandboxed or non-global installation where available.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description is broad enough to trigger on common user questions such as 'how do I do X' or 'can you do X', which can cause the skill to activate in many ordinary conversations. In this skill's context, over-triggering is risky because activation can lead to recommending or initiating installation of third-party packages, expanding the attack surface and increasing the chance of unnecessary or unsafe installs.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation criteria include vague conditions like asking 'how do I do X', 'can you do X', or expressing interest in extending capabilities, without clear boundaries for when to prefer direct assistance over external skill discovery. Because this skill is tied to a package-install workflow, ambiguous activation can steer normal support requests into external search and installation paths the user did not explicitly request.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs the agent to install packages globally with '-g' and bypass prompts with '-y', but does not require a trust review, source verification, or warn that this changes the user's environment. In a skill-discovery context involving third-party sources, this meaningfully increases the risk of silent installation of untrusted code and persistent system-level modifications.

VirusTotal

66/66 vendors flagged this skill as clean.