Back to skill

Security audit

项目规划

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward project-planning skill with no bundled code, hidden execution, or deceptive behavior.

Before installing, expect this skill to guide project plans and progress tracking in Chinese. If you let it use files, calendars, reminders, or web search, require confirmation before it saves project data, creates reminders/events, or sends project details to external services.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage example "我已经完成资料搜集,更新一下项目进度" is a generic conversational request that could arise in many contexts, but the README does not define any narrower activation constraints or exclusion conditions. Without specificity on when this skill should activate versus a general assistant response, it risks unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Phrases like "帮我重新排期", "我应该做什么?", and "帮我复盘" are common expressions that are not uniquely tied to this skill. The README provides examples but no explicit constraints, trigger list, or non-trigger cases, making the activation condition ambiguous.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description includes broad trigger examples such as “今天做什么” and “项目进度,” which can occur in ordinary conversation and may cause unintended invocation outside a clearly bounded project-planning context. The manifest does not provide exclusion conditions or negative examples to clarify when these phrases should not activate the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and all user-facing instructions are written exclusively in Chinese, and the example triggers and responses assume Chinese output by default. There is no indication that the user may choose another language or locale, which can violate organizational language-choice policy.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Several listed activations, including “我现在做到这里了” and “我今天应该做什么,” are ambiguous unless the user is already inside an established project session. The file says these expressions “均应进入项目规划流程” but does not define contextual limits, increasing the risk of false activations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill encourages use of files, calendars, reminders, web search, and other tools, but does not require explicit user confirmation before making persistent or external actions. Even though it says not to falsely claim actions were completed, it lacks a safety rule to obtain consent before saving data, creating reminders, or invoking external resources, which can lead to unintended system changes or privacy-impacting operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language instructions and examples are all in Chinese, and the file does not indicate that users may interact in other languages or that the skill is intentionally limited to a Chinese-language audience. Under the stated policy, forcing a specific language without opt-in can be a locale policy violation.

Content

No source excerpt is available for this finding.