Back to skill

Security audit

生物错误DNA

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese K12 biology learning-analysis skill with scoped profile use, explicit consent controls, and no executable or hidden install behavior.

Install this for Simplified Chinese, China-aligned K12 biology use. Operators serving other regions should localize crisis resources, curriculum assumptions, and minor-consent rules before deployment; users should review the profile, sharing, parent-summary, and reminder consent settings because the skill can participate in long-term learning records when authorized.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger examples include broad, emotionally phrased requests such as '帮我分析生物错误规律' and '我生物是不是没救了', which can match ordinary conversation beyond a clear request to use this specific skill. In an education context this can cause unintended invocation, leading to unnecessary access to profile/archive functions or misrouting a user away from the most appropriate skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest and instructions are entirely in Chinese and present user-facing trigger phrases and response behavior only in Chinese. There is no indication that the user can choose another language or that the Chinese-only constraint is an explicitly documented, justified locale limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The schema's user-facing natural-language fields such as note and description are written only in Chinese, which imposes a single language/locale in a shared distributed schema. There is no accompanying indication of user choice, multilingual support, or a documented region-specific justification for the locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document states that the library is designed for Mainland China Chinese K12 scenarios, with simplified Chinese phrasing and China-specific help channels as defaults. This is a language/locale constraint stated as a default operating policy rather than a user choice or explicit opt-in, which matches the policy-violation category for locale restrictions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file is entirely written in Chinese and establishes repository-wide vocabulary and usage rules as the sole source of truth. There is no indication that users or downstream skill operators may choose another language or locale, which can constitute a language/locale policy violation under the stated rules when no opt-in or alternative is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The schema's human-readable note and description are written entirely in Chinese, and the enumerated status/value descriptions throughout the file also assume a Chinese locale. For a shared protocol schema, this creates a language-specific constraint in natural-language documentation without any indication of user opt-in or justification for a locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.