Back to skill

Security audit

persona-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only persona-generation helper with no evidence of hidden access, persistence, or unsafe behavior.

Installers should understand this is a Chinese-documented persona-generation skill for UX or human-factors work. Review outputs for assumptions, especially when no real research data is provided, but no special security controls are indicated by the artifact.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description and usage instructions are entirely in Chinese, and the usage section implies the interaction flow directly in that language without mentioning any user language option. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions include very broad natural-language requests such as asking for persona or target-user analysis, which can overlap with ordinary conversation and cause the skill to activate when the user did not explicitly intend to invoke it. This can lead to scope hijacking, where the assistant prematurely switches into a rigid persona-generation workflow, asks unnecessary follow-up questions, or transforms user content in ways that are not aligned with the original request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The instruction states that output language defaults to matching the user's input language, with Chinese input producing Chinese output. This creates a language behavior policy without explicitly offering the user a choice or opt-in, which can be a locale/language policy concern under the stated rules.

Content

No source excerpt is available for this finding.