Back to skill

Security audit

skill-guidelines

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese-language guidance skill for creating and reviewing agent skills, with no executable code, network behavior, credential handling, or hidden persistence.

Install this if you want Chinese-language guidance for designing or reviewing agent skills. Reviewers who do not read Chinese should translate or request an English version before relying on it, but the inspected artifact does not show risky execution or data-access behavior.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language instructions and usage guidance are presented in Chinese, which can impose a language constraint on users without any opt-in or stated justification. The policy requires flagging language or locale restrictions unless the skill offers a language choice or clearly documents the reason for the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and trigger text are written entirely in Chinese, while the file provides no indication that language selection is optional or that the skill is intentionally restricted to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README says the skill is triggered when creating, reviewing, or optimizing a skill via the skill name skill-guidelines, but it does not clarify narrower activation conditions, exclusions, or concrete examples of when it should not be used. For a markdown file, this can make invocation scope ambiguous even though the skill name itself is fairly specific.

Content

No source excerpt is available for this finding.