Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 不要求用户理解 `SKILL.md`、metadata、I/O、workflow 这些词。
Security audit
duange-zero-skill
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language helper for creating Codex skills, and its files are coherent, disclosed, and proportionate to that purpose.
Install this if you want a Mandarin onboarding flow for creating Codex skills. Review generated skills carefully before distributing them, especially if they involve credentials, publishing, deleting files, payments, or external services.
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 (12)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 不要求用户理解 `SKILL.md`、metadata、I/O、workflow 这些词。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 不要求用户理解 `SKILL.md`、metadata、I/O、workflow 这些词。
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 不要求用户理解 `SKILL.md`、metadata、I/O、workflow 这些词。
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The README states the assistant helps users '用普通话' turn ideas into a skill, which implies a fixed language requirement without presenting a choice. This is not a classic security flaw, but in agent routing it can lead to mismatched handling, user confusion, and exclusion of users who did not consent to Chinese-only interaction.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger phrases are broad, generic requests like '帮我做一个小助手' and '我想做一个 Skill', which can match many ordinary conversations and cause the skill to activate unintentionally. In an agent environment, overbroad routing can hijack unrelated requests, expose users to unexpected prompt flows, or interfere with safer/more appropriate skills.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file explicitly instructs the skill to '用普通话提问', which imposes a specific language choice in the skill's behavior. The policy allows locale or language constraints only when the user is offered a choice or when the restriction is clearly justified as region-specific, neither of which is present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The file presents all example prompts and trigger guidance exclusively in Chinese, which can amount to an implicit language policy for the skill. There is no indication that users may interact in other languages or that the Chinese-only scope is intentional for a region-specific use case.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill’s instructions and example prompts are entirely in Chinese and direct the conversation in that language, with no indication that users may choose another language. This creates a language/locale policy concern because it imposes a specific language by default rather than offering user opt-in or alternatives.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The template uses a generic activation phrase ('当用户说某些触发词时使用') without requiring concrete, bounded triggers. In a skill-creation context, this can propagate ambiguous activation logic into generated skills, increasing the chance of unintended invocation, context hijacking, or execution in situations the user did not intend.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The usage section placeholder ('当用户……') leaves activation conditions underspecified, encouraging downstream skills to rely on broad natural-language matching. Because this repository is meant to help non-technical users create skills, the ambiguity is more dangerous: users are less likely to add precise guardrails, making accidental or overbroad activation more likely.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The description states the skill is for users and is written entirely in Chinese, implying a fixed language/locale experience. Under the policy, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy issue.
- Content
Static analysis
No suspicious patterns detected.