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（样例本身就是一张自洽的押金台账）
Security audit
押金保证金收取与退还核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local rent deposit ledger checker with disclosed, purpose-aligned behavior and no evidence of network use, persistence, or hidden mutation.
Install only if you are comfortable using a Chinese-language local CLI tool for deposit/refund ledger checks. It processes ledger text locally and does not change accounting systems, but its output is advisory and should be verified against contracts, bank records, and internal policy before business action.
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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)
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（样例本身就是一张自洽的押金台账）
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（样例本身就是一张自洽的押金台账）
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s user-facing comments, prompts, and result text are entirely in Chinese, including input guidance and disclaimer language. There is no indication that users may choose another language or that the locale restriction is optional or region-specific, which can violate a language-choice policy.
- Content