Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
广告文案合规预检（免费）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese advertising-copy checker that reads user-provided text and reports limited absolute-term findings without network use or persistence.
Install only if you need a local Chinese advertising absolute-terms pre-check. Treat results as a limited mechanical screen, not legal advice or a complete advertising-law review; broader sensitive-word, medical, finance, education, real-estate, and bulk checks are explicitly outside this free version.
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
- 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 (10)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
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：
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
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：
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 81% confidence
- Finding
- The visible title, summary, description, and usage guidance are overwhelmingly presented in Chinese, while the English description is minimal and does not provide equivalent operational guidance. This effectively constrains the skill to a specific language experience without an explicit user opt-in or a clearly documented locale-policy justification.
Vague Triggers
Medium
- Confidence
- 89% confidence
- Finding
- The trigger list includes broad phrases such as '敏感词检测' and '广告法检查', which can cause the platform to invoke this narrowly scoped skill for much broader compliance-review requests than it actually handles. This creates a skill-routing and scope-confusion risk: users may receive incomplete compliance results while believing a comprehensive review was performed, which is especially problematic in regulatory contexts.
Natural-Language Policy Violations
Medium
- Confidence
- 89% confidence
- Finding
- This code file contains user-facing natural-language descriptions and result strings entirely in Chinese, framing the skill as operating only in that language and legal context. There is no indication of a user choice or opt-in for language/locale, which can violate organizational language/locale policy when a skill implicitly forces a specific language.
Natural-Language Policy Violations
Medium
- Confidence
- 92% confidence
- Finding
- The JSON contains only Chinese promotional copy and provides no indication that the language is optional, user-selected, or required for a region-specific use case. This creates a natural-language locale policy concern because it hardcodes a specific language without opt-in or justification.
Natural-Language Policy Violations
Low
- Confidence
- 95% confidence
- Finding
- The natural-language interface, help text, status messages, and capability description are entirely in Chinese, with no indication that users may choose another language or locale. The policy specifically calls for flagging language or locale constraints when they are imposed without user opt-in or clear justification.
Static analysis
No suspicious patterns detected.