ClawHub
Back to skill

Security audit

Compression Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for checking agent behavior after context compression, with no bundled code, persistence, credential use, or hidden actions.

Installers should understand this as a monitoring and measurement guide, not a complete bundled toolset; verify any referenced external scripts or framework integrations before running them from another source.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill’s trigger list ends with a broad catch-all phrase that can match almost any task involving agent consistency or session boundaries, making activation overly permissive. In agentic systems, this can cause the skill to be invoked in unintended contexts, creating prompt-scope creep, increasing attack surface, and potentially interfering with more appropriate skills or workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.