ClawHub
Back to skill

Security audit

Ifa Help Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local documentation lookup helper for iFA Evolution help files, with no evidence of exfiltration, persistence, destructive behavior, or hidden high-impact authority.

Install only if you use iFA Evolution local help files on a matching Windows setup. Expect to adjust the hardcoded paths and clean up the encoding or missing reference files for best results; the reviewed artifact does not show unsafe behavior.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Hidden Instructions

High
Category
Prompt Injection
Confidence
86% confidence
Finding

The file begins with a hidden/unexpected Unicode character (BOM/zero-width style artifact), which can conceal instructions, break parsers, or cause inconsistent interpretation across tools. In prompt-driven systems, hidden characters increase review difficulty and can be used to smuggle content past simple validation or signature checks.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: ifa-help-query
description: "Search and extract iFA Evolution help system documentation �� function descriptions, interface pa..."
tags: [domain-specific, plc, template-based, file-based, cli]

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to produce output in Chinese without indicating that this should depend on user preference or locale. This can override user intent, reduce usability, and create misleading behavior in multilingual environments, especially when the user expects another language for safety-critical or technical documentation.

Content

No source excerpt is available for this finding.