Ae1
High
- Category
- analysis-evasion
- Content
# 第一步：把 scripts/analyze.py 脚本保存到本地
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
广告数据分析
Security checks for vulnerabilities and agentic risk
Overview
This skill locally analyzes user-provided advertising spreadsheets and generates local charts, with no evidence of hidden network access, persistence, or credential handling.
Install this if you want a Chinese-language local analyzer for advertising Excel/CSV reports. Use it on reports you intentionally provide, review generated optimization suggestions before acting on them, and be aware it will install standard Python data-analysis packages and write chart images to the chosen output folder.
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 (5)
Ae1
High
- Category
- analysis-evasion
- Content
# 第一步：把 scripts/analyze.py 脚本保存到本地
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Vague Triggers
Medium
- Confidence
- 95% confidence
- Finding
- The skill advertises activation on very broad phrases like '帮我分析投放数据', '看看这个报表', and '数据有没有问题', which can match common user requests beyond a tightly scoped advertising workflow. This increases the chance of unintended invocation on arbitrary spreadsheet/report analysis, causing the agent to process files or requests the user did not intend for this skill, with possible privacy and workflow-integrity impact.
Natural-Language Policy Violations
Medium
- Confidence
- 85% confidence
- Finding
- The skill metadata and documentation are entirely in Chinese and describe the skill in a way that implies Chinese-language interaction, but they do not state that language choice is optional or region-specific. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.
Natural-Language Policy Violations
Medium
- Confidence
- 98% confidence
- Finding
- The file’s docstring, CLI description, help text, and runtime output are all written in Chinese, which imposes a specific language on users. Under the policy, forcing a language or locale without opt-in is a natural-language policy violation unless the constraint is explicitly justified.
Static analysis
No suspicious patterns detected.