Back to skill

Security audit

Human Traits Learning

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill with no executable files, installers, network behavior, or hidden persistence, though its localized documentation is mislabeled or incomplete.

Installers should treat this as low-risk documentation. Users should be aware that some advertised localized files are not actually translated, and any adaptation to user preferences should only be done with explicit user consent.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (10)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all contributor-facing instructions in Chinese, but does not indicate that the skill is region-specific or provide an opt-in language/locale choice. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file’s natural-language content is effectively restricted to Chinese, including headings, guidance, and safety instructions. Under the policy, forcing a specific language without user opt-in or a documented justification is a locale/language policy violation.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SECURITY.md (reported line 17)May include surrounding context.

md
- ❌ Does NOT collect user data without explicit consent
- ❌ Does NOT make external network requests
- ❌ Does NOT access system files or resources
- ❌ Does NOT execute arbitrary code or commands
- ❌ Does NOT store or transmit personal information
- ❌ Does NOT require any system-level tools (curl, kubectl, etc.)
- ❌ Does NOT use environment variables for configuration

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document under i18n/ar/ presents its usage guide heading in Chinese (纯文档使用指南), and the rest of the content is also written in Chinese rather than Arabic. This creates a language/locale policy issue because the file appears to target Arabic localization but forces a different language without user opt-in or any documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file is located under an Arabic i18n path, but the title and guide content are written in Chinese, which creates a language/locale mismatch. The document does not provide a user choice of language or explain why Chinese is required, which violates the language/locale policy criterion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This file is located under an English i18n path, but nearly all instructional content is written in Chinese. That can effectively force a specific language on users without opt-in or an explicit explanation, which matches the language/locale policy violation criterion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file is located under the English i18n path, but nearly all user-facing guidance is written in Chinese. This creates a language/locale policy issue because the skill effectively imposes a specific language on users without offering a choice or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file path indicates a Spanish localization (i18n/es), but the instructional heading at L03 is written in Chinese. This imposes a specific language on the user without opt-in or explanation, which is a natural-language locale policy issue under the stated rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file path indicates a Spanish internationalization guide (i18n/es), but the visible heading is written in Chinese (用户指南). This creates a language/locale mismatch that effectively imposes a specific language on users without offering a choice or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This file is located under a French i18n path but the heading and subsequent guidance are written in Chinese, which effectively imposes a specific language on the user. The document does not offer a language choice or explain a justified region-specific constraint, so it conflicts with the language/locale policy criterion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.