Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Security audit
工资表发放前核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local payroll-sheet checking skill that is coherent with its stated purpose and does not show network use, persistence, credential access, or hidden destructive behavior.
Use this only with payroll data you intend to process locally through the Node script. The skill is Chinese-language and its trigger wording is broad, so review when it activates in general payroll discussions, but the inspected package does not send data out or install persistent components.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list includes broad terms such as '算薪' and 'HR 对账' that can plausibly appear in general payroll or accounting conversations unrelated to this specific verification skill. Over-broad invocation can cause the skill to activate unexpectedly on sensitive payroll discussions, increasing the chance of unintended processing or disclosure of salary data.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file’s user-facing documentation and operational guidance are entirely written in Chinese, and later return messages are also hard-coded in Chinese. There is no indication that the skill supports language choice or that the Chinese-only behavior is an explicitly documented regional constraint, which matches the locale-policy violation criteria.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The user-facing capability description, usage text, help output, and runtime messages are entirely in Chinese, with no indication that another language can be selected. This creates a language/locale policy issue because the skill effectively imposes a specific language on users without opt-in or documented justification.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The comment states that invalid JSON will be treated as plain-text material, giving '直接粘贴的合同全文' as an example. That contradicts this skill's stated payroll-checking purpose and the rest of the file, which consistently expects a payroll table with headers. This is an intent/documentation mismatch rather than merely incomplete documentation.
- Content