Back to skill

Security audit

meta-cognitive-architecture-reconstruct

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local graph-analysis helper with a small persistent learner file, but it does not show hidden execution, credential access, network use, or destructive behavior.

Install only if you want a Chinese-language local graph-refactoring helper and are comfortable with its learner writing a small JSON memory file in the skill directory. Do not pass secrets or sensitive private notes into the learner field unless you are comfortable retaining them locally.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The repeated mismatch indicates the skill is framed as a broad, superior meta-skill while apparently only providing a narrower graph-refactoring workflow with limited self-test behavior. Overstated capability can mask what the skill really does, especially if it writes local state or telemetry, and can cause users or orchestrators to grant elevated trust, autonomy, or data access under false assumptions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The repeated mismatch indicates the skill is framed as a broad, superior meta-skill while apparently only providing a narrower graph-refactoring workflow with limited self-test behavior. Overstated capability can mask what the skill really does, especially if it writes local state or telemetry, and can cause users or orchestrators to grant elevated trust, autonomy, or data access under false assumptions.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill advertises operational behavior that appears to include file-writing capability, but it declares no explicit tool scope or permissions boundary. In an agent ecosystem, missing permission declarations can let a caller or runtime grant broader-than-expected access, making file persistence or state mutation occur without clear review or containment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s natural-language description and instructions are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. This creates a language/locale policy concern because it effectively imposes a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The module docstring is written in Chinese and presents the skill purpose only in that language, which can indicate a language-specific behavior without user opt-in. There is no accompanying indication that users may choose another language or that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script appends a caller-controlled note to a persistent JSON file with no validation, truncation, consent prompt, or retention controls. While this is not code execution, it creates a privacy and integrity risk because sensitive user input can be stored indefinitely, and repeated large inputs can grow the file unexpectedly or poison downstream logic that trusts learned_patterns.json.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Python file contains its primary description, usage guidance, comments, assertion messages, and output strings in Chinese, which imposes a specific language on users and maintainers. The file does not indicate that Chinese is optional, user-selectable, or required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.