Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security audit
待办大师
Security checks for vulnerabilities and agentic risk
Overview
This is a local todo manager that stores tasks in a user-confirmed local SQLite database, with no evidence of hidden network access, credential use, or destructive behavior.
Install only if you are comfortable with the skill creating a config file and a local SQLite todo database in the directory you confirm. The reference docs appear outdated, so rely on SKILL.md and the CLI behavior for the current SQLite-backed design.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (8)
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The manifest description is entirely in Chinese and the skill instructions/examples throughout the file are written only in Chinese, which indicates a language-specific constraint. There is no opt-in, alternative language option, or justification that this skill is intended only for a Chinese-speaking or region-specific context.
Intent-Code Divergence
Medium
- Confidence
- 96% confidence
- Finding
- L005 将该 skill 描述为“本地文件驱动”且“在不依赖数据库”的情况下运行，但本次技能清单上下文明确声明该技能实际使用 Python CLI 和 SQLite 存储。该文档不是单纯信息缺失，而是对存储实现方式作出了相反表述，容易误导审计者和调用方对数据行为的理解。
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The document specifies that `created_at` and `updated_at` use timezone-aware timestamps with a default China timezone. This is a locale policy concern because it forces a specific regional setting without indicating user choice, opt-in, or a region-specific justification.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The document specifies a default Asia/Shanghai timezone for timestamps, and later uses China local date for overdue calculations and locks this as a product decision. This imposes a specific locale policy on all users without offering a choice or clearly documenting that the skill is intended only for a China-specific context.
Missing User Warnings
Low
- Confidence
- 88% confidence
- Finding
- This markdown file states that `data/` is auto-created after initialization and that task data is persisted to local JSON files, but it does not explicitly warn users that using the skill will create and modify files on disk. Because SQP-2 applies to markdown files when behaviour could affect user data or system integrity, a brief disclosure about local filesystem writes would improve safety transparency.
Natural-Language Policy Violations
Low
- Confidence
- 94% confidence
- Finding
- The file sets `DEFAULT_TIMEZONE = "Asia/Shanghai"`, which imposes a specific locale-dependent behavior for due dates and time handling. The skill does not present this as a user choice or document an opt-in path in this file, so it risks violating language/locale neutrality expectations.
Description-Behavior Mismatch
Low
- Confidence
- 77% confidence
- Finding
- The manifest enumerates initialization, CRUD-style todo management, filtering, status transitions, archiving, and schema migration, but does not mention a separate `stats` capability. The code adds a summary/reporting operation that computes aggregate counts and urgency metrics, which is additional behavior not reflected in the stated description.
Static analysis
No suspicious patterns detected.