Back to skill

Security audit

App Data 所有对话 主对话 中级会计备考大师 V5.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese intermediate-accounting exam tutoring skill made of Markdown study materials, with no executable code, network calls, install hooks, or hidden privileged behavior found.

Install this if you want a Chinese-language tutor for intermediate accounting exam prep. Be aware that it describes maintaining an error book of your incorrect answers, so avoid entering sensitive personal information unless the host app clearly explains storage, deletion, and retention.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description and role/instruction text are entirely in Chinese and define the assistant as a Chinese exam-prep tutor, with no indication that users may choose another language. This is a natural-language locale policy concern because the skill appears to mandate a specific language experience without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This file specifies all instructions, triggers, outputs, and user-facing behavior exclusively in Chinese, effectively forcing a language/locale without user opt-in. Under the policy, language constraints should either offer user choice or be explicitly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions use very generic study-oriented phrases such as requests to generate practice or exercises, which can overlap with ordinary user requests in broader conversations. In an agent environment, this can cause unintended command routing and skill invocation, making the agent follow a rigid SOP when the user did not actually intend to invoke this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This trigger relies on generic phrases like asking how to prepare, study plans, or insufficient time, which are common across many tutoring or productivity contexts. Such ambiguity increases the risk of accidental activation and incorrect routing, especially in multi-skill assistants where unrelated educational or planning requests may be captured by this accounting skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The routing table contains broad catch-all matching, including generic terms and an 'other accounting-related questions' fallback, which can overcapture user input and steer the model into strict predefined behavior. This is dangerous because overly broad routing increases unintended invocation risk and reduces the model's ability to safely clarify ambiguous intent before acting.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file states that the system will automatically record users' incorrect answers, answer history, and related learning data, but it provides no notice about consent, retention period, deletion policy, storage scope, or sharing boundaries. This creates a privacy and compliance risk because educational performance data can be personal data, and users are not told how it is handled or how long it persists.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file presents all instructions and framework content exclusively in Chinese, and it does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user 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
86% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown resource forces a specific language throughout the file, and there is no indication that users can opt into another language or that the Chinese-only scope is explicitly justified as a region-specific tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill file is written in Chinese and presents all instructional content in that language, without indicating that the user can choose another language or that the file is intentionally limited to a Chinese-language audience. Under the natural-language policy check, this is a locale/language constraint that is not explicitly opt-in or justified in the file itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all user-facing instructional content exclusively in Chinese, and nowhere indicates that the user may choose another language or that the skill is intentionally limited to a Chinese-speaking or China-specific audience. 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
86% confidence
Finding

SQP-3 applies to all file types and covers natural-language language/locale policy violations. This file presents all instructional and descriptive content only in Chinese, and it does not offer users an opt-in choice of language or explicitly justify that the skill is limited to a Chinese-language or China-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire file is written in Chinese and does not indicate that users may choose another language or that the Chinese-only presentation is required for a region-specific or compliance-specific purpose. Under the stated policy, a skill that fixes language/locale without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.