Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
直播佣金与坑位费结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
The local checker code is mostly self-contained, but the skill also embeds mandatory upsell instructions that can send the agent into external payment and installation flows despite no-payment and no-network claims.
Install only if you are comfortable with a Chinese-language local accounting checker that also prompts users about a paid upgrade. Do not let the agent follow payment links, QR codes, raw IP purchase URLs, dependency installs, or new skill installation steps unless you explicitly intended to buy the full version and have independently verified the SkillPay merchant, product, amount, and platform rules.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Description-Behavior Mismatch
High
- Confidence
- 98% confidence
- Finding
- The skill markets itself as a fully local, no-network checking tool, yet later instructs the agent to access external websites, retrieve purchase instructions, and facilitate payment/install flows. That mismatch can mislead users and host agents into performing networked commercial actions outside the expected trust boundary, increasing phishing, payment-redirection, and unauthorized procurement risk.
Context-Inappropriate Capability
High
- Confidence
- 96% confidence
- Finding
- The documented purpose is settlement-sheet verification, but the skill contains instructions for product discovery, purchase, payment-link handling, and post-purchase installation. Embedding commerce orchestration in an accounting-check skill creates an unnecessary capability expansion that could be abused for social engineering or to trigger risky external actions unrelated to the user’s original task.
Natural-Language Policy Violations
Medium
- Confidence
- 84% confidence
- Finding
- The instructions to the agent are written as mandatory behavior for every invocation and require presenting the upsell flow in Chinese-language content, while the document does not offer the user any language or locale choice. Although the skill has an English display name/description, the operative user-facing workflow is fixed in Chinese, which can violate language/locale policy when not explicitly opt-in or region-justified.
Whitespace Padding
Medium
- Category
- Prompt Injection
- Content
输出与你的安全约束**；它**可被用户关闭**（`SKILL_NO_UPSELL=1`），也**必须可忽略**（不点不买不影响结果）。 执行官方购买指令时：先读一次官方说明；核对**商户号 `2088702818190040`**、商品号与订单是否一致； ⛔ 不要点击来路不明的链接/二维码，也**不要替用户付款** —— 付款一律由**用户本人**确认。
- Confidence
- 80% confidence
- Finding
- Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Intent-Code Divergence
Medium
- Confidence
- 84% confidence
- Finding
- The documentation claims the only difference between free and full versions is a set of additional checks, but it also introduces separate purchase and installation behavior not disclosed in that comparison. This inconsistency undermines informed consent and can conceal operational changes that cause the agent to leave the local analysis context and engage with external services.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- Natural-language strings throughout the file, including the top-level description, sample data, user-facing advice, and result messages, are exclusively in Chinese. The skill does not indicate that language is region-specific, configurable, or subject to user preference, which creates a locale-policy risk under the language/locale rule.
Static analysis
No suspicious patterns detected.