ClawHub
Back to skill

Security audit

Short Form Video Script Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent writing helper for short-form video scripts and does not contain code, hidden execution, credential use, or persistence mechanisms.

Installers should treat this as a persuasive copywriting aid. Review generated claims for accuracy before publishing, especially claims about products, metrics, or availability, and provide explicit audience, runtime, and CTA preferences to keep outputs on scope.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger section is broad enough to match generic writing, rewriting, idea generation, captions, and performance analysis requests without clear exclusion criteria. In an agent environment, this can cause the skill to activate outside its intended scope, override more appropriate skills or system behaviors, and steer outputs toward persuasive short-form marketing content when the user asked for something more general.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 390)May include surrounding context.

md
Not just create tasks — the full layer. Route them, assign them, date them. Promote ideas into projects. Surface what's overdue. Move things around.

But what actually makes it work is the judgment. It acts on the obvious without checking in. Only asks when a detail would actually change the outcome.

You just talk to it like it's a full-time operator on your team. It figures out the rest — what list, who it goes to, when it's due. No defining, no navigating. You say the thing and it handles it.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The instruction "Never explain what the tool is. Talk like a peer." imposes a fixed communication style for builder/peer audiences without offering any user choice or exception. This is a natural-language policy concern because it forces a particular presentation approach rather than making tone optional or context-dependent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.