Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（内置一张干净的月度巡查表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
消防设施检查与维保记录核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language checker for fire-safety inspection records and does not show hidden networking, persistence, or unrelated data access.
Install only if you work with Chinese fire-safety inspection or maintenance records and are comfortable running a local Node.js checker. Review the listed free-version limits: it performs record/table consistency checks, not a legal, technical, or on-site safety certification.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（内置一张干净的月度巡查表）
- 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（内置一张干净的月度巡查表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
- The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The file’s natural-language interface, examples, labels, advice, and outputs are entirely in Chinese, indicating the skill is designed to operate only in that language. There is no user-facing opt-in, language selection, or documented justification that this is a region-specific compliance tool, so this creates a locale/language policy concern.
Natural-Language Policy Violations
Low
- Confidence
- 87% confidence
- Finding
- The primary display name, summary, and descriptions are presented in Chinese, and the usage/documentation throughout the file is Chinese-only except for a brief English description field. This can be read as a locale/language constraint without explicit user opt-in or a clear statement that the skill is region- or language-specific.
Intent-Code Divergence
Low
- Confidence
- 90% confidence
- Finding
- The comment says non-JSON input is treated as plain-text material, giving '直接粘贴的合同全文' as an example, which suggests broad document handling. But the rest of the script is explicitly limited to fire-safety inspection/maintenance records with required headers and reports insufficient input otherwise, so the inline documentation overstates what the code meaningfully supports.
Static analysis
No suspicious patterns detected.