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
租金收缴与欠租台账核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language rent ledger checker that discloses its free-version limits and does not show network access, persistence, or hidden behavior.
Install only if you are comfortable using a Chinese-language local checker for rent collection ledgers. Treat its output as table arithmetic and consistency assistance, not accounting, tax, legal, or contract advice, and note that several advanced checks are explicitly reserved for the full version.
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 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
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
- 89% confidence
- Finding
The visible skill name, summary, primary descriptions, examples, and usage context are presented almost entirely in Chinese, while only a minimal English label/description is provided. This creates a language constraint without an explicit user opt-in or statement that the skill is intentionally region- or language-specific.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill text presents conflicting statements about what the free version actually checks: earlier it says the free version runs whatever the engine declares as free, while later it says specific checks are not included and that the only difference from the full version is that list. This can mislead users or downstream agents about detection coverage, causing them to rely on the tool for controls it may or may not perform. In a financial reconciliation skill, ambiguous scope can produce false assurance and missed accounting issues.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s user-facing natural-language content—including comments describing behavior, error/advice strings, findings messages, and disclaimer text—is entirely in Chinese. There is no indication that the skill is region-specific or that users can opt into another language, which creates a locale policy concern under the natural-language policy rule.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The user-facing natural-language strings, usage instructions, and operational messages are entirely in Chinese, and there is no indication that another language is supported or that the user can opt into a preferred locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON sample consists entirely of Chinese headers and values in the natural-language content, which implies a fixed language/locale. For a general-purpose skill artifact, this can violate language/locale policy when no user opt-in, alternative locale, or justification is provided.
- Content