ClawHub
Back to skill

Security audit

Visual Essay Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only content-structuring skill for visual essays, with no code execution, persistence, credential use, or hidden system access.

Install this if you want a bilingual English/Chinese visual-essay packaging workflow. If you prefer another language or single-language captions, explicitly tell the agent to adapt the template; no security-sensitive access or automatic publishing behavior was found.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The prompt explicitly requires English captions first and Chinese captions second for each image, which imposes a specific language requirement. Under the policy, forcing a locale or language without offering user choice or documenting a justified regional need is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This section requires both an English and a Chinese artist statement and does not provide any user choice about language. That creates a fixed language policy in the skill instructions, which is disallowed unless the constraint is explicitly justified or optional.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The template explicitly requires both English and Chinese fields such as "SERIES TITLE (EN)" and "SERIES TITLE (CN)" as well as bilingual artist statements. This imposes a specific language/locale requirement in the skill content without any visible indication that the user can choose languages or opt in to bilingual output.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The captions and closing-line template requires both "EN" and "CN" entries for output sections. Because no justification or user-choice mechanism is provided, this appears to force a language policy rather than offering locale flexibility.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The description states captions are generated as "EN first, CN second," which imposes a fixed language/locale format rather than offering a user choice. The file does not indicate that users can opt into or change this language pairing, which may conflict with language-choice policy expectations.

Static analysis

No suspicious patterns detected.