Back to skill

Security audit

产品经理PRD工具

Security checks for vulnerabilities and agentic risk

Overview

This skill is a PRD-writing helper that reads or edits user-selected product requirement documents, with no hidden network, credential, persistence, or executable-code behavior found.

Install this if you want an agent to create and maintain PRD Markdown files. Before using clarify or extend mode, make sure the path points to the intended PRD because the skill is designed to save edits directly; ask for English explicitly if you do not want Chinese output.

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
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises broad trigger phrases such as '需求文档' and related common expressions, which can cause the agent to activate in contexts where the user did not clearly request this skill. Because the skill can create or modify files, accidental invocation increases the chance of unintended file writes or PRD edits from ambiguous everyday conversation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill performs write operations by default, including creating new files and directly modifying existing PRDs during clarify and extend flows, but it does not require an explicit user confirmation immediately before persisting changes. In an agent setting, this can lead to silent or unexpected overwrites, especially when mode detection is based on ambiguous arguments or inferred intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

L360 规定“除非用户明确要求英文,PRD 内容一律用中文撰写”,这属于默认强制特定语言的行为。根据规则,若未明确提供语言/locale 选择或 opt-in,这种语言策略构成自然语言政策违规。

Content

No source excerpt is available for this finding.