ClawHub
Back to skill

Security audit

Factory Acceptance Test

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for drafting factory acceptance test plans and reports, with no executable behavior or hidden authority.

Installers should treat this as a drafting aid for manufacturing acceptance documentation and verify AQL tables, regulatory requirements, and final acceptance decisions with qualified quality personnel before use.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

md
- [ ] Do not write "inspect to AQL 1.0" without the sample size and accept/reject numbers — that phrase settles nothing
- [ ] Do not let critical defects carry a non-zero acceptance number
- [ ] Do not judge cosmetics against memory or photos alone — physical limit samples or it will be relitigated every lot
- [ ] Do not allow rework-and-reinspect of a rejected lot without 100% rescreen of the reworked defect mode
- [ ] Do not accept a lot with an unsigned deviation in the log
- [ ] Do not let golden samples go stale across an ECO — refresh or they certify the wrong product

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says to use the skill when asked to "write a FAT plan," "define outgoing quality inspection," or "document FAT results." While FAT-specific phrasing is narrow, phrases like "define outgoing quality inspection" and "document FAT results" are broad enough that they may match general QA-writing requests without clear boundaries or exclusion conditions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.