T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
skill.yaml:11- Finding
Execution Sandbox Explicitly Disabled Without Operational Need
- Content
View full analysis
- Remediation
View remediation
Security audit
Solution Architect
Security checks for vulnerabilities and agentic risk
Overview
The skill appears to be a Chinese-language business framework CLI, but it disables execution sandboxing without a functional need.
Review before installing because the skill asks to run its Python entry point without sandbox isolation despite only needing simple local CLI behavior. If you use it, prefer enabling sandboxing and removing the unused PyYAML dependency; also treat the business frameworks as Chinese-language reference material and verify data-source, licensing, privacy, and platform-terms compliance before implementing any recommended automated data collection.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (2)
T08 · Insecure Dependencies
Note
- Location
skill.yaml:42- Finding
Unused and Unpinned PyYAML Dependency Expands the Supply-Chain Attack Surface
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (9)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The entire skill description, examples, and usage guidance are presented only in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest description and the entire user-facing documentation are written in Chinese, and the file does not indicate that other languages are supported or that Chinese is an optional locale. Under the policy rule for natural-language violations, a skill that effectively constrains interaction to a specific language without opt-in should be flagged.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This Python file contains natural-language descriptions, help text, and examples presented only in Chinese, which effectively forces a specific language for users. The policy allows fixed language only when users are given a choice or when the locale restriction is explicitly justified, neither of which appears here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The manifest sets the skill language to zh-CN, which indicates a fixed locale preference. There is no accompanying note that users may select another language or that the locale restriction is optional or justified as region-specific.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file’s natural-language content consistently uses Chinese for all headings, instructions, and framework descriptions, and it does not indicate that users may choose another language. Under the policy criteria, forcing a specific language without user opt-in can be a locale policy violation unless the restriction is explicitly justified.
- Content
Context-Inappropriate Capability
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The manifest describes a solution-architect skill that provides validated business frameworks, tactics, implementation roadmaps, and KPI systems. In contrast, the enhance flow introduces a local file access capability via --my-plan and Path(...).exists(), even though the function never actually analyzes the file contents and the stated purpose does not require filesystem interaction.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This manifest file includes general-purpose usage scenarios such as having a business problem, goal, or plan, but it does not specify clear invocation constraints, trigger boundaries, or negative examples. In a routing system that uses manifest text to decide activation, these broad descriptions could overlap with many ordinary requests and cause unintended invocation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
SQP-3 适用于所有文件类型，包括 markdown。该文件从标题到全文均强制使用中文表述，但没有说明这是面向中文用户/中文业务场景的限定，也未提供用户可选择其他语言或本地化形式的说明，存在语言/locale 策略上的潜在约束。
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The document explicitly recommends automatic collection of financial reports, announcements, research reports, news, and social-media sentiment data, but provides no guardrails around lawful collection, platform terms, personal data handling, or downstream compliance review. In a real deployment, this omission can lead operators to implement scraping or ingestion pipelines that violate site terms, process personal data improperly, or create regulatory exposure, especially when social-media data is involved.
- Content