Back to skill

Security audit

胡田 OPC导师 量子电池 英文版

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a quantum-battery knowledge base, but it asks agents to rewrite its persistent reference files and includes prescriptive investment guidance without strong user controls.

Review this skill before installing if you expect English-only content or regulated financial-advice safeguards. Use it as educational due-diligence material, not personalized investment advice, and disable or require explicit confirmation for any self-heal/write behavior that would modify bundled reference files.

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 (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:292
Finding

Automatic Modification of Trusted Knowledge Files Without Integrity Controls

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file title says '英文版' (English version) on L01, but the substantive content from L03 onward is written in Chinese. This creates a language/locale policy concern because the skill documentation effectively forces a specific language without offering the user a choice or documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly describes writable operations on local knowledge-base files and a self-heal mechanism that can rewrite content, but it does not require clear user consent, constrain write scope, or define safety checks before modification. In an agent environment, this can lead to unintended local file changes, silent data corruption, or persistence of bad/generated content if the skill is triggered on a real workspace.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file materially diverges from the declared skill purpose: instead of an English due-diligence framework, it is a Chinese-language investment guide containing explicit investment recommendations, timing advice, sector preferences, and portfolio allocation suggestions. This mismatch can mislead users and downstream systems about the skill’s scope, increasing the chance that financial advice is surfaced where users expected neutral assessment content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This section gives concrete portfolio construction advice, position sizing, and strategy recommendations for different risk appetites before any meaningful warning is presented. Users may treat these allocations as endorsed financial advice, which is especially risky in a skill framed as due diligence rather than licensed investment advisory content.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The metadata names the skill as an English version, but the title, overview, scenarios, and usage instructions are predominantly in Chinese. This creates a natural-language policy concern because the skill appears to impose a language choice without explicitly offering users a language or locale option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains user-facing natural language entirely in Chinese, including the title, headings, and all definitions, but does not indicate that the user can choose another language or that the glossary is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file's natural-language content is fully Chinese from title to body, 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 audience. Under the policy, forcing a specific language without user 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
91% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that the language is optional, user-selected, or required for a specific regional/compliance purpose. Under the natural-language policy rule, forcing a specific language without user opt-in can be a locale policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that the user can choose another language or that the document is intentionally limited to a Chinese-speaking audience. Under the language/locale policy check, a skill artifact that implicitly enforces one language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The title and entire document are written in Chinese, which imposes a specific language/locale on the user without any stated opt-in or alternative. Under the policy criteria, natural-language content that forces a language can be a locale-policy violation unless the constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.