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（干净样例 0 命中）
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 carbon-emissions report checker whose code and instructions match its stated purpose and do not show hidden network use, persistence, credential access, or destructive behavior.
Before installing, note that the tool is primarily Chinese-language and expects copied table text or JSON containing carbon-emissions report data. It appears to run locally without network use, but users should still avoid treating its output as a formal audit or regulatory determination because the skill itself says it only performs table-internal arithmetic and consistency 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 (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（干净样例 0 命中）
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（干净样例 0 命中）
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.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file’s user-facing description, usage text, errors, and output strings are entirely in Chinese, and there is no indication that users may choose another language. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The primary display name, summary, and main descriptions are presented in Chinese, and the body of the skill documentation is also entirely Chinese except for a brief English metadata line. Although an English description field exists, the skill does not state that users may choose their preferred language, which can violate a language/locale choice policy when no opt-in is offered.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The comment on L075 says non-JSON content is treated as '纯文本材料（例如直接粘贴的合同全文）', using a contract document as the example. Everywhere else in the file, the skill is described as operating on carbon emission reports and activity-data tables with headers, so this documentation suggests a broader document type than the implementation intent presented by the manifest and usage text.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The file's only user-facing natural-language content is entirely in Chinese, including headers, labels, and notes, with no indication that language selection is optional. Under the language/locale policy rule, forcing a specific language without user opt-in can be a policy violation unless clearly justified as region-specific.
- Content