prompt-compress

Security checks across malware telemetry and agentic risk

Overview

This skill appears to only analyze and compress user-provided prompt text, without hidden access, persistence, network activity, or destructive behavior.

Install only if you want an agent to help shorten prompts. Review compressed prompts before sending them onward, especially for legal, medical, security, or complex instructions where removing nuance could change the meaning.

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: 90% confidence
Finding: The trigger list contains broad, common phrases such as ‘优化提示词’, ‘关键词提取’, and ‘减少token’, which can plausibly appear in ordinary conversation and cause the skill to activate when the user did not explicitly intend to invoke it. In a prompt-processing skill, unintended activation is risky because it may rewrite or compress user instructions, dropping safety-relevant nuance or constraints before the content is sent onward.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal