ClawHub
Back to skill

Security audit

Compression Monitor

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for checking agent drift after context compression, with no bundled code or hidden execution behavior.

Install only if you want guidance for monitoring long-running agents after compression. Treat any session logs as sensitive, probe only agents you control, and separately review any external Python scripts or repository code before running them.

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
95% confidence
Finding
The skill’s trigger list ends with a broad catch-all phrase, effectively matching 'any task involving verifying agent behavioral consistency across session boundaries.' This can cause the skill to be invoked outside its narrowly intended scope, increasing the chance it is selected in unrelated workflows and influences agent behavior or analysis where it is not appropriate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.