Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Security audit
广告文案合规预检（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese advertising-copy checker with narrow, disclosed behavior and no evidence of network access, persistence, credential use, or hidden actions.
Install only if you need a Chinese-language, local pre-check for absolute advertising claims. Do not treat it as full legal review or as coverage for medical, finance, education, real estate, broad sensitive-word, or general advertising-law compliance checks.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (10)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 脚本本身不做计算，真正的检查在同目录的 `scripts/engine/ad-compliance.js`（纯 Node 标准库，CommonJS），可以直接引用：
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 脚本本身不做计算，真正的检查在同目录的 `scripts/engine/ad-compliance.js`（纯 Node 标准库，CommonJS），可以直接引用：
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The skill metadata and user-facing content are presented entirely in Chinese for operation, while the file also contains English metadata, suggesting broader distribution but no explicit statement that the skill is Chinese-only or region-specific by design. Under the policy, language constraints should be opt-in or clearly documented and justified.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The trigger list is unusually broad for a narrowly scoped ad-compliance skill and includes generic phrases such as 敏感词检测, 违禁词检查, and 广告法检查 that could match many unrelated moderation or compliance requests. This can cause inappropriate invocation or routing, leading users to rely on a tool that only checks absolute advertising terms while omitting other requested compliance categories.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This code’s natural-language interface is consistently fixed to Chinese, including docstrings, status advice, messages, labels, findings, and disclaimers. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified; this file does not present such an opt-in or clear region-specific constraint as an interface policy.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file's user-facing help, capability name, status messages, and usage instructions are entirely in Chinese, which imposes a specific language on users. There is no opt-in, alternate locale, or explanation that this skill is intentionally region-specific, so this is a natural-language locale policy issue.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON contains only Chinese promotional text and provides no indication that language choice is optional or limited to a justified region-specific use case. This can violate language/locale policy because it imposes a specific language without user opt-in.
- Content