ClawHub
Back to skill

Security audit

zmg-srew

Security checks for vulnerabilities and agentic risk

Overview

This is a simple storyboard-writing skill with no code execution, persistence, credential access, or hidden data handling.

Before installing, users should know this skill defaults to a Chinese storyboard template and may activate for a range of creative video-script requests. It appears appropriate for storyboard drafting and does not show sensitive access or execution 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broadly phrased across many common creative tasks (news topics, campaigns, documentaries, short videos, brand stories, outlines), which can cause over-triggering and unintended invocation. In an agent environment, this may route ordinary user requests into this skill when a more appropriate or safer skill should handle them, increasing the chance of confusing outputs, missed policy checks, or prompt-scope hijacking.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill title and output format constrain the interaction toward Chinese without offering user choice or documenting a justified locale requirement. This can override user intent, degrade usability, and in multi-skill systems create prompt-routing or instruction-priority conflicts where the skill imposes a language unexpectedly, potentially causing misunderstanding in production or compliance-sensitive contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broad enough to match a wide range of generic creative-writing or scripting requests, which can cause the agent to invoke this skill outside its intended narrow use case. Over-broad routing increases the chance of context hijacking, irrelevant tool use, and unintended disclosure of user content into a specialized workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hardcodes Chinese output structures and headings without documenting locale selection or asking for user language preference. This can override user intent, produce unusable output for non-Chinese contexts, and create prompt-routing ambiguity where the skill imposes an unexpected language transformation on otherwise safe requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.