T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
skill.yaml:11- Finding
Unnecessary Unsandboxed Skill Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Leadership Coach
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese leadership-coaching CLI, but it unnecessarily disables sandbox isolation and declares an unused unpinned dependency.
Install only if you are comfortable with a Chinese-language local CLI running outside sandbox containment. The publisher should enable sandboxing and remove or pin the unused PyYAML dependency before this is treated as low-risk.
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:38- Finding
Unused and Unpinned PyYAML Dependency Expands the Supply-Chain Attack Surface
- Content
View full analysis
- Remediation
View remediation
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 (9)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill documentation is written entirely in Chinese, including all usage examples and operational guidance, and it does not indicate that users may choose another language. Under the policy, a skill that effectively requires a specific language without opt-in or justification is a natural-language policy violation.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The manifest and README repeatedly state that the skill provides complete, unselected coverage of all five leadership solutions, including '工作效率 26 条'. However, this section is explicitly labeled '精选条目' and lists only a handful of items, directly contradicting the stated intent of complete, non-curated coverage.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The version history claims '工作效率 26 条' is included as a complete set and reiterates that all rules are presented without selection. Earlier in the same file, the productivity section is explicitly marked as a selected subset, so the documentation contradicts itself about the skill's actual content.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This markdown skill applies to all users but its description forces a specific language/locale experience by presenting the skill solely in Chinese. The file does not offer user opt-in, alternate language support, or a documented region-specific justification, which matches the language/locale policy-violation criterion.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The markdown file consistently uses Chinese for the description, headings, guidance, and examples, which effectively forces a specific language on users. Under the policy, a language constraint should either be optional for the user or explicitly documented and justified as region-specific.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The manifest description and top-level heading present the skill entirely in Chinese, with no indication that users may choose another language or locale. This creates a natural-language policy concern because the skill appears to impose a specific language by default rather than documenting a justified locale restriction or offering opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This code file contains the primary skill description and CLI help text in Chinese, and the command outputs throughout the script are likewise Chinese-only. Because the skill does not offer any language selection or explain that it is intentionally region-specific, it creates a locale-policy concern under the natural-language policy rules.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest explicitly sets the skill language to "zh-CN", which indicates a fixed language/locale requirement. Under the policy, locale constraints should either offer user opt-in/choice or be clearly justified as region-specific; neither is present here.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The manifest and module docstring emphasize that the skill provides complete leadership solutions with all laws listed, not curated selections. However, the
planaction intentionally shows only the first 5 items and tells the user to use another command for the rest, which contradicts the stated '不精选'/'完整版' positioning for what the skill provides directly.- Content