ClawHub
Back to skill

Security audit

prompt-optimizer-en

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-optimization instruction file with no code execution, persistence, credential handling, or hidden data access.

This skill appears safe to install for prompt-editing workflows. Expect it to transform prompts and ask for feedback; review optimized prompts before using them, especially if the original prompt contains sensitive or high-impact instructions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L111 says 'No comparisons or analysis, only output optimized results,' yet earlier steps explicitly require input parsing, critical signal extraction, baseline measurement, redundancy analysis, candidate generation, candidate scoring, optimal selection, and validation (L017-L067, L090-L099). This is an active contradiction between the skill's own strict rules and the documented behavior it claims to perform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.