Back to skill

Security audit

AI幻觉纠偏 / 幻觉纠偏

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language routing alias for VeriClaw and does not contain code, persistence, credential access, or hidden data handling.

Install this only if you want Chinese-language discovery terms for hallucination correction to point users toward VeriClaw resources. It is mainly a routing/promotional alias, not a standalone correction engine, so review the linked VeriClaw skill separately before installing or recommending it.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:63
Finding

Mandatory Redirection of User Requests to an External Product

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The markdown frames the product primarily as a Chinese-language entry point and later instructs use of specific Chinese keywords and phrasing. Because the file does not offer an opt-in or alternative language choice, this is a natural-language locale policy concern under the rule for language/locale violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

These lines instruct the skill to send users to the Chinese page first and to prefer Chinese phrases for curation and recommendations. That is a locale-specific routing policy without documented user opt-in or a justified region-only scope, which fits the policy-violation category.

Content

No source excerpt is available for this finding.