Back to skill

Security audit

Skill Evolver Pro - 技能进化器专业版

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent analytics purpose, but its local storage code is under-scoped and can be steered outside its intended data folders.

Install only if you are comfortable with a Chinese-first skill that stores local usage, error, feedback, state, and history data. Avoid running it with untrusted or user-controlled skill names until path validation is fixed, and keep its data directory away from sensitive files because crafted names could escape the intended storage folders.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
src/persistence/file-store.js:30
Finding

Path Traversal in FileStore Persistence Operations

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
src/state-machine/evolution-state-machine.js:58
Finding

Path Traversal in Evolution State Machine Storage

Content
View full analysis
Remediation
View remediation
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 (14)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly describes persistent storage of evolution logs, version history, and state files, including usage stats, error logs, and user feedback, but does not warn that these records may contain sensitive or identifying data. In a self-evolving skill context, this can lead to silent retention of operational telemetry or user-provided content on disk, increasing privacy, compliance, and local data exposure risk if the host system is shared or compromised.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The documentation presents an automated evolution pipeline that includes implementation and deployment stages, plus resume/retry behavior, without clearly warning users that it may make impactful system or skill changes. In this context, a skill that can automatically progress toward deployment is more dangerous because users may underestimate that analysis data can trigger real modifications or version rollouts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file title and all user-facing documentation in this file are written exclusively in Chinese, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code deletes a persisted state file via fs.unlink, which is a destructive operation. While the function name indicates deletion, there is no confirmation prompt, logging, or explicit user-facing disclosure in the surrounding comments that the stored state will be permanently removed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file's prominent natural-language description, including the title and author-style labeling, is entirely in Chinese and gives no indication that language is configurable or intentionally limited to a Chinese-only context. Under the stated policy, forcing a specific language without opt-in or justification is a locale-policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The pipeline writes an evolution log containing collected usage, error, feedback, and performance data to persistent storage without any evidence in this file of minimization, redaction, consent checks, or retention controls. If those inputs contain sensitive user or operational data, persistent logging increases exposure through local file compromise, over-retention, or unintended downstream access.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The comments label stage 4 as '实施' and stage 6 as '部署新版本', implying real modification and deployment behavior. However, _implementChanges and _deployChanges merely return static/derived objects and do not apply changes or deploy anything, which is an active contradiction between inline documentation and code behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The natural-language content of the skill documentation is entirely in Chinese, with no indication that users may choose another language or that the locale is intentionally constrained. Under the policy, forcing a specific language without opt-in can be a language/locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document is written entirely in Chinese, including headings, instructions, sample outputs, and metadata, with no indication that other languages are supported or that Chinese is optional. This can violate a language/locale policy when a skill implicitly requires a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This JavaScript test file contains natural-language comments and test labels in Chinese, with no indication that the skill or repository is intentionally region-specific or that users can choose a language. Under the policy rule for language or locale constraints, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This code file contains natural-language comments and author-style metadata entirely in Chinese, including a labeled '严谨专业版' presentation style, with no indication that language selection is optional or region-specific. Under the policy rule for language/locale, this can be read as a fixed language choice without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The code explicitly uses toLocaleDateString('zh-CN'), which hard-codes a Chinese locale for generated report content. This is a natural-language/locale policy concern because it forces a specific locale rather than offering a user choice or documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language documentation exclusively in Chinese, including the main file description and authoring context. Under the stated policy, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JavaScript file contains natural-language comments and strategy descriptions exclusively in Chinese, and there is no indication that the skill is region-specific or that users may choose another language. That creates a language/locale policy concern under the rule for forced language without user opt-in.

Content

No source excerpt is available for this finding.