ClawHub
Back to skill

Security audit

Vn NSFW Sensory Lexicon

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Vietnamese erotic-writing lexicon with no code or system access, but it includes under-disclosed coercive/refusal-themed sexual guidance that warrants Review before installation.

Review this skill carefully before installing. It does not appear to access your system or data, but it may cause an agent to generate explicit sexual content involving distress, refusal, or coercive framing unless the user gives stricter consent and safety boundaries.

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 (2)

Ssd 4

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly instructs users to stage female expression as a progression from embarrassment to arousal to orgasm, while elsewhere providing resistance/pleading cues such as 'stop', 'pull out', and 'forgive me' alongside continued sexual action. In context, this normalizes non-consensual or coercive sexual content and can be used to generate assault-themed narratives that reinterpret refusal as arousal.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly defines the skill as a 'Vietnamese Sensory Vocabulary Engine,' which imposes a specific language on generated content. The file does not provide any opt-in, alternative language path, or policy justification for restricting output to Vietnamese.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.