Back to skill

Security audit

Mystilink Ziwei

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Zi Wei astrology charting skill with explicit local calculation and optional Wiki lookup behavior, but users should be mindful of birth-data privacy if using the external Wiki workflow.

Install only if you are comfortable providing birth datetime, timezone, gender, and optional location data to a local charting script. Treat the Wiki lookup as external network use and send only minimal derived terms, not full birth profiles, unless you intentionally want that data included.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (9)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · .gitignore (reported line 18)May include surrounding context.

text
.idea/
.vscode/
*.log
.env
.env.*
!*.env.example

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The declared purpose and the detected behavior diverge significantly: the skill appears to perform broader computations, profile/file I/O, and undeclared astrology-related processing while not implementing parts of the promised interpretation workflow. This mismatch is dangerous because reviewers and policy engines may approve or expose the skill under a narrower trust model than its actual capabilities, increasing the chance of unintended data handling, overcollection, or misuse of file and processing features.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code emits user-facing CLI descriptions, errors, and chart output entirely in Chinese, including fixed strings in the parser help text and printed results. The skill does not provide any language or locale opt-in mechanism, which is a natural-language policy concern when a skill mandates a specific language for all users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

La ligne indique qu’en l’absence de locale Wiki, la valeur par défaut est en avec un repli éventuel zh-Hans. Cela constitue une contrainte de langue/locale imposée sans mention d’un choix explicite de l’utilisateur, ce qui correspond à une violation de politique en langage naturel.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README states that the Wiki API is optional and involves network access, but it does not clearly warn users that birth-chart-related terms or other request data may be sent to an external service. For markdown files, network behaviors that may affect privacy should be disclosed with a user-facing warning.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The workflow includes direct external HTTP requests to a third-party Wiki API but does not explicitly warn that user prompts, chart facts, or derived birth-profile information could be transmitted off-host. In the context of an astrology skill handling sensitive personal birth data, even optional network lookups can create privacy risk if operators assume the workflow is fully local.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explicitly documents optional network calls to an external Wiki API but does not warn that user-supplied birth/profile context or derived chart terms could be transmitted off-host. In a divination/astrology skill, birth data is sensitive personal information, so missing privacy disclosure and data-minimization guidance can lead to unintended exposure even if the API call is only for interpretation lookup.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The examples for both search and page retrieval explicitly use locale=en, which suggests the skill defaults to English content without presenting a user choice. This can violate language/locale policy when a skill constrains output or retrieved content to a specific locale absent documented opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.