Back to skill

Security audit

aiq-assessment

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AI capability assessment skill with no executable code, network access, credential handling, or hidden persistence, though users should be careful with privacy and report-file handling.

Install only if you want a Chinese-language AIQ assessment workflow. Before using it for candidates, employees, or teams, make sure you have permission and avoid pasting confidential conversations unless appropriate. Confirm the report path before file output and do not overwrite existing files unintentionally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad phrases such as '会不会用AI' and generic capability-assessment wording, which can cause the skill to activate in ordinary conversations not actually requesting this specific assessment workflow. Unintended activation can lead to inappropriate data collection prompts or unsolicited evaluation behavior, especially in sensitive contexts like hiring or performance review.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The usage conditions describe many broad scenarios but do not define firm boundaries for when the skill should refuse to activate or ask for confirmation. In practice, this ambiguity increases the chance of over-triggering, including on third-party evaluations or organizational audit scenarios where consent, privacy, and scope should be established first.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to write a report file to a default path in the current working directory and then deliver it, without requiring explicit user confirmation or warning about creation/overwrite behavior. This can cause unintended file creation, accidental overwriting of an existing file, or disclosure of sensitive assessment content to an unsafe location.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written only in Chinese, with no indication that users may choose another language or that the framework is intentionally limited to a Chinese-speaking audience. Under the policy, a fixed language/locale without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.