Back to skill

Security audit

小五子 - 基因修复

Security checks for vulnerabilities and agentic risk

Overview

The skill is only a short Markdown instruction file, but it describes unattended automatic rollback and instruction self-repair without clear limits or user approval.

Review this skill before installation if you expect strict human control over agent changes. It should be used only where autonomous rollback or prompt/instruction repair is intended, and preferably after adding clear limits on what state it may modify and when confirmation is required.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly describes automatic rollback and self-healing behavior that can modify agent behavior or system state, but it does not warn users that autonomous changes may occur or define boundaries for when such changes are permitted. In an unattended automation context, silent self-modification or rollback can conceal failures, override operator intent, or introduce unsafe state changes without review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The natural-language content of the skill appears to require Chinese comprehension, and there is no indication that users may choose another language or that the Chinese-only presentation is required for a specific regional context. This can violate language or locale policy where user opt-in or justification is expected.

Content

No source excerpt is available for this finding.