Back to skill

Security audit

生物实验探究教练

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese K12 biology experiment tutoring skill with clearly disclosed optional profile, wrong-answer, and reminder handoffs.

Install this for Chinese-language mainland China K12 biology experiment coaching. Review whether optional student profile memory, cross-skill sharing, wrong-answer handoff, and reminder queueing match your deployment's consent and localization requirements, especially outside mainland China.

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
  • 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 (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description, labels, and all user-facing instructions are written exclusively in Chinese, and the skill does not state that language choice is optional or limited to a China-specific deployment. Under the policy, forcing a specific language without user opt-in 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
95% confidence
Finding

The file presents all instructional content in Chinese and does not indicate that users may choose another language or that the skill is restricted to a Chinese-speaking or region-specific audience. The policy for this audit flags language or locale constraints when they are imposed without user opt-in or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This JSON schema contains natural-language policy-relevant strings entirely in Chinese and also constrains multiple user-facing fields to Chinese-only enum values elsewhere in the schema. Because the file does not state that the skill is region-specific or that users can opt into this locale, it appears to enforce a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

该 markdown 文件通篇以中文规定技能参数与适用性说明,但未见任何允许用户选择语言/地区表达方式的说明,也未说明该语言限制仅适用于特定区域或受众。根据规则,强制特定语言而无用户 opt-in 可构成自然语言层面的组织政策违规。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says '错题归档与计数(转通用错题本)', indicating this biology inquiry coach should not itself implement wrong-answer handling as part of its scope. But this distributed schema explicitly includes the 'wrong_answer_handover' path and fully defines a wrong-answer payload for this skill, which expands behavior beyond the stated instructional role into error-tracking transfer semantics.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest describes the skill as explaining biology experiment design, steps, controls, conclusions, and exam-operation precautions. This schema also authorizes 'reminder_enqueue' with rich reminder scheduling fields, which is a separate productivity/notification capability not described as part of the skill's teaching purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill guidance, including operational instructions and user-facing phrasing examples, is written exclusively in Chinese and does not indicate that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The document is entirely written as a mandatory shared vocabulary and contract in Chinese, with wording that all skills and schemas must reference this single source. There is no indication that Chinese is optional, user-selected, or justified as a region-specific constraint, which can amount to a language/locale policy violation under the stated rules.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The natural-language metadata and descriptions are written entirely in Chinese, including the title/description context and operational notes, with no indication that this schema is intentionally restricted to a Chinese-only environment or that users can opt into another language. Under the policy, a forced language/locale without opt-in or explicit justification can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.