Back to skill

Security audit

Nạp liệu

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed adult fiction transformation skill with no code execution, network use, credential access, or persistence, though users should apply it only to clearly eligible adult content.

Install only if you specifically want a Vietnamese/Chinese adult-fiction rewrite helper. Use it on content where all characters and context are clearly appropriate for adult sexualized rewriting, and review outputs carefully because the triggers can intensify mild scenes.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and instructions are written to operate in a specific Vietnamese/Chinese locale context without indicating any user-consent or fallback behavior. Forced locale behavior can produce incorrect formatting, mismatched language output, or surprising transformations for users who did not request that language mode.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger "Mọi chapter" applies the transformation to every chapter without any narrowing conditions, making activation scope overly broad. In this skill, that broad scope is especially risky because it directs systematic insertion of explicit sexual content, increasing the chance of unintended or policy-violating output whenever the skill is used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger includes an open-ended catch-all phrase ("các hành động ôm ấp nhẹ"), which makes it ambiguous and easy to over-apply beyond the enumerated cases. Because the skill's behavior is to replace mild affectionate actions with explicit sexualized actions, this ambiguity can cause unsafe escalation on inputs that were not clearly intended for that treatment.

Content

No source excerpt is available for this finding.