ClawHub
Back to skill

Security audit

SAAS Worker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SaaS-building guidance document with only inert placeholder support files and no hidden execution, persistence, or data access behavior.

Install only if you want opinionated SaaS launch guidance. Review any agent actions involving payments, customer outreach, public posting, or production changes before approval, because those are business-impacting even though this skill does not automate them secretly.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description claims a broad operational skill for building and scaling SaaS products, but the actual code does not implement any such functionality. It only prints a static example message and includes comments indicating it is a placeholder. This is a material description-to-behavior mismatch because the code lacks the declared primary purpose and capabilities.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.