ClawHub
Back to skill

Security audit

ARTICLE_TO_VIDEO_SCRIPT

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward writing template for turning pasted articles into video scripts, with no executable code, persistence, credential use, or hidden data access.

Installers should expect this skill to shape the agent's writing style and final formatting for video scripts. Users who need non-English output or a different editorial voice should state that explicitly when invoking it.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Use soft subscribe/comment/follow phrasing.
- Keep CTA low pressure.

## Output Rules

Return only the final script.
- No process explanation.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The style rules require a specific writing style and implicitly fix the output language to English throughout the skill description, with no provision for respecting the user's preferred language or locale. This can violate language/locale policy when users provide non-English source material or expect output in another language.

Static analysis

No suspicious patterns detected.