Back to skill

Security audit

Quality Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language quality-review workflow that reads/checks deliverables and may ask other agents to review them, with no executable code or hidden persistence found.

Install this if you want a Chinese-language deliverable QA workflow that can trigger broad review steps and involve additional review agents. Before using it on non-Chinese, non-academic, confidential, or cost-sensitive work, confirm the file scope, desired citation/style rules, and whether multi-agent review should run automatically.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises automatic triggering for very broad terms like '质检', '验收', '交叉检查', and applies to nearly all formal deliverables. This can cause the pipeline to activate unexpectedly on unrelated tasks, spawning extra agents and causing unintended file access, context expansion, or workflow interference without a narrowly scoped user request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The section explicitly prescribes Chinese journal formatting conventions such as Chinese fonts and GB/T 7714 citation format, and the overall document is written as mandatory guidance rather than an optional locale-specific profile. Because no user opt-in or alternative language/locale path is provided, this creates a natural-language locale policy constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate whether users may request another language or whether the Chinese-only scope is intentional. Under the language/locale policy rule, a skill-facing document can be flagged when it implicitly enforces one language without opt-in or documented justification.

Content

No source excerpt is available for this finding.