Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（干净样例 0 命中）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
碳排放报告数据核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language carbon-emission report checker whose code matches its stated purpose and does not show hidden network, persistence, credential, or destructive behavior.
Install this only if you are comfortable running a local Node script against pasted carbon-emission report data. It appears to keep data local and not require registration, payment, API keys, or network access, but its interface and results are primarily in Chinese and it is limited to the six disclosed checks.
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 (9)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（干净样例 0 命中）
- 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（干净样例 0 命中）
- 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
- 90% confidence
- Finding
- The primary display name, summary, and main descriptions are written in Chinese, and the document content is entirely Chinese except for a brief English description field. This creates a language/locale constraint in the skill's user-facing instructions without an explicit opt-in or statement that users may choose another language.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- This JavaScript skill is entirely described in Chinese, and its returned advice/messages are also hard-coded in Chinese. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified; this file does not present such a user choice or explicit locale-only constraint.
Natural-Language Policy Violations
Medium
- Confidence
- 91% confidence
- Finding
- All user-facing descriptions, usage text, errors, and output strings in this file are written exclusively in Chinese, and the skill does not provide any opt-in or alternative locale handling. That can violate a language/locale policy when users are not explicitly told the skill is Chinese-only or given a language choice.
Intent-Code Divergence
Low
- Confidence
- 91% confidence
- Finding
- The inline documentation says non-JSON input is handled as '纯文本材料（例如直接粘贴的合同全文）', but the rest of the file consistently describes the expected input as carbon-emission report and activity-data material with headers. This is an active documentation contradiction, not just an omission, because it suggests a different document type than the skill's stated domain.
Natural-Language Policy Violations
Low
- Confidence
- 96% confidence
- Finding
- The only natural-language content in this manifest-style JSON is a large fixed text block entirely in Chinese, with no indication that the skill offers alternative languages or that the Chinese-only locale is an intentional, documented regional constraint. Under the policy for natural-language violations, forcing a specific language without user opt-in is reportable.
Static analysis
No suspicious patterns detected.