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
货运险投保与货损理赔核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local cargo-insurance ledger checker with no network use, credential handling, file writes, or persistence found.
Install only if you want a Chinese-language, local Node-based checker for cargo-insurance ledger text. Review the free-versus-withheld checks before relying on results, and provide only ledger data you are comfortable processing locally on this machine.
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 (6)
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
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
Vague Triggers
Medium
- Confidence
- 88% confidence
- Finding
- The manifest description says the trigger phrases include "货损理赔", which is a broad domain phrase rather than a specific invocation. Because no exclusion conditions or narrower activation constraints are given, this could cause the skill to activate for general discussion of cargo-damage claims, not just ledger-checking requests.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- This JavaScript skill’s comments, sample input schema, prompts, advice, and disclaimer are entirely in Chinese, and the code requires Chinese header names such as “运单号 / 保单号 / 货值 ...” in the input guidance. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not stated here.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The JSON payload consists entirely of Chinese column headers and status values, with no indication that language selection is optional or that the file is intended only for a Chinese locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Static analysis
No suspicious patterns detected.