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
生产投入产出与报废率核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local, deterministic table-checking skill with no evidence of network use, persistence, credential access, or hidden execution, though users should notice its Chinese-only interface and one inconsistent disclaimer line.
Install only if a Chinese-language, local Node-based checker for production yield and scrap tables fits your workflow. Do not treat it as a full production-control audit: the free version explicitly omits several checks, including inter-process quantity matching, and its results should be reviewed against the checks_not_run list.
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
- 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
Findings (8)
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
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This file’s comments, prompts, advice, sample input expectations, and result messages are all written in Chinese, including the required input column names and user guidance. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the restriction is explicitly justified as region-specific, which is not stated here.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The disclaimer claims the tool checks inter-process consistency ('上工序产出 = 下工序投入'), but no such logic is implemented in the code path. In an accounting/production-control validation skill, this can create false assurance that a key reconciliation was performed, causing users to miss material discrepancies between process stages.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
All user-facing strings, help text, and operational messaging in this file are written exclusively in Chinese, with no indication that another language can be selected. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The JSON content is entirely in Chinese and provides no indication that language selection is optional or constrained by a documented region-specific requirement. Under the policy rule for natural-language violations, forcing a specific language without user choice can be non-compliant.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The manifest-facing fields such as display name, summary, tags, and main description are written in Chinese, with only a brief English description provided later. This can create a de facto language constraint for discovery and use without explicitly offering the user a language choice or stating that the skill is Chinese-language only.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The comment states that non-JSON input will be treated as plain-text material such as a '合同全文' (full contract text). That documented example contradicts the rest of the script and manifest, which are specifically scoped to checking production yield/scrap tables with headers, not arbitrary contract documents.
- Content