Security audit

产品经理技能

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable product design methodology skill with no evidence of hidden access, persistence, credential handling, or unsafe automation.

Installers should expect a Chinese product-design workflow reference. Users who need another language should request it explicitly, but there is no artifact-backed evidence of malicious or high-impact behavior.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill begins by mandating Chinese output ('根据产品经理的需要...输出...') without indicating that language should follow user preference or allow opt-in. This can override or conflict with a user's requested language, reducing usability and potentially causing misunderstanding in downstream product, research, or PRD work, but it does not create a direct security compromise.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.