Back to skill

Security audit

Human-AI Closed Loop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language workflow for structuring human-AI feedback loops, with no artifact-backed evidence of hidden execution, exfiltration, or destructive behavior.

Install this if Chinese-language workflow instructions are suitable for you and you are comfortable storing project feedback in local loop_log-style records. Avoid putting sensitive private data into feedback logs unless your runtime confirms those logs stay local.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents core operational instructions and user-facing reminder text entirely in Chinese, including the checklist, trigger conditions, and alert message. Under the policy rules, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all user-facing instructions and descriptions exclusively in Chinese, with no indication that other languages are supported or that the user can choose their preferred language. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description in L05 is written entirely in Chinese, and the document continues with Chinese section headings and examples without indicating that users may choose another language. This creates a natural-language locale constraint that is not presented as optional or justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains user-facing procedural content exclusively in Chinese, including headings, checklist items, and pass/fail criteria. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which this file does not provide.

Content

No source excerpt is available for this finding.