Back to skill

Security audit

Skill Validator 4f8f6e

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese Markdown guide with no code, install steps, persistence, or sensitive access.

Installation appears low risk. Be aware that its broad trigger terms may make it appear during unrelated skill or how-to requests, so narrowing the trigger would improve usability.

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
96% confidence
Finding

The trigger string includes very generic terms such as '如何使用' and 'skill', which can match ordinary user requests unrelated to this specific skill. Overbroad activation can cause the wrong skill to run, leading to unintended instruction injection into unrelated conversations and reducing routing safety.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation rule says the skill should trigger when the user 'needs skill-validator related help' without defining what qualifies as related. This ambiguity increases the chance of accidental invocation, which can override more appropriate skills or inject irrelevant guidance into normal user interactions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language content throughout the file assumes Chinese as the required interaction language, but there is no opt-in, alternative language option, or explanation that the skill is intended for a Chinese-only audience. This can violate language or locale policy when a skill forces a specific language implicitly.

Content

No source excerpt is available for this finding.