ClawHub
Back to skill

Security audit

Skill Distiller (One-Liner)

Security checks for vulnerabilities and agentic risk

Overview

This is a small, disclosed skill for compressing skill markdown, with no evidence of hidden execution, persistence, credential use, or data exfiltration.

Install this only if you want an agent to create shorter versions of skill files. Because it intentionally removes lower-value sections based on an LLM judgment, review the compressed output before replacing any original skill content.

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
Confidence
91% confidence
Finding
The trigger condition is phrased broadly enough that ordinary user requests to summarize, shorten, or reduce content could invoke this skill unintentionally. In a skill that rewrites or removes sections based on an LLM importance judgment, accidental activation can cause inappropriate compression of unrelated content, loss of safeguards, or unintended transformation of user material.

Static analysis

No suspicious patterns detected.