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
工会经费与残保金计提核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local-only Chinese finance table checker and its requested file and Bash access are proportionate to that purpose.
Install only if you are comfortable using a Chinese-language local CLI for this specific accounting table. The package appears to run locally without network use, registration, API keys, or persistence, but users should review the free-tier limitations because several checks are explicitly not included.
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 (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
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The primary display names, summary, tags, and main descriptions are written entirely in Chinese, while the only English description is brief and does not provide equivalent operating guidance such as triggers or usage details. This creates a language-specific user experience without explicit opt-in or a documented justification for restricting the skill to Chinese.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The file’s user-facing comments, descriptions, examples, and guidance are entirely in Chinese, including the main skill purpose and operating instructions. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which this file does not do.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The user-facing natural language throughout the script, including the title, usage, errors, and output messages, is entirely in Chinese, and there is no indication that users may select another language. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The inline documentation says non-JSON input is handled as plain-text material such as a '合同全文' (full contract text). That contradicts the rest of the file, which consistently states the skill only checks 工会经费与残保金计提表 with headers and should reject insufficient/non-matching materials rather than implying contract documents are valid input.
- Content