ClawHub
Back to skill

Security audit

AI SaaS Demo Script

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI SaaS demo-script and storyboard helper; its real-UI capture guidance is purpose-aligned but users should avoid including confidential product data.

Install only if you want help creating SaaS product demo scripts or video storyboards. When using it with private apps, provide sanitized screenshots or staging data where possible, avoid secrets/PII/customer records in captures, and review any generated video assets before sharing.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The guidance explicitly encourages capturing real UI text, assets, screenshots, and private product states, but it does not require consent checks, data minimization, or redaction of confidential information before those materials are reused in scripts, storyboards, or outputs. In a demo-video pipeline, this can expose sensitive business data, customer information, internal workflows, or proprietary assets to downstream prompts, files, and rendered media.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The invocation text uses a natural-language pattern ('turn this AI SaaS feature into a concise product demo video script') without clarifying boundaries, exclusions, or alternative non-trigger phrasing. Although somewhat domain-specific, the manifest does not define when the skill should or should not activate, which can lead to unintended invocation in adjacent product-marketing conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.