Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
银行贷款利息与还款计划核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language loan interest and repayment table checker with limited, disclosed checks and no evidence of network use, persistence, credential access, or hidden behavior.
Install only if you are comfortable using a Chinese-language local checker for copied/exported loan repayment table text. Treat results as limited to the listed free checks and do not rely on it for excluded loan, contract, LPR, accounting, tax, or legal judgments.
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
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill documentation presents conflicting claims about what the free version checks versus what it explicitly excludes. In a financial verification skill, this can mislead users into relying on controls that are not actually performed, causing missed errors in loan interest or repayment calculations and creating audit/compliance risk.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The file’s natural-language instructions, disclaimers, and user-facing messages are entirely in Chinese, which effectively constrains interaction and outputs to a single language/locale. The skill does not mention any user opt-in, alternative language support, or that the locale restriction is intentional and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The only natural-language content in this manifest-style JSON value is Chinese, with no indication that language selection is optional or tied to a justified region-specific use case. The policy requires flagging locale or language constraints when they are imposed without user opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This code file contains extensive natural-language help, usage, and status messages only in Chinese. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless a justified region-specific constraint is documented, which is not present here.
- Content