Back to skill

Security audit

pua-debugging-pro

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only debugging workflow is purpose-aligned and does not install code, persist itself, handle credentials, or move data; the main caveat is mixed English/Chinese templates.

Installers should know this skill will push the agent to keep debugging with evidence, validation, and bounded escalation before stopping. Review the Chinese-language templates if your team expects English-only output, but no executable or privileged behavior was found.

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
  • 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
  • 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 entire skill file is written as a Chinese-only postmortem template, and it does not indicate that language choice is optional or user-selectable. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The 'User Clarification Request' template is entirely written in Chinese and provides no indication that the language should match user preference or be configurable. This creates a natural-language policy issue because it imposes a specific language on downstream user-facing responses without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.