ClawHub
Back to skill

Security audit

Qa Retrospective

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Chinese QA retrospective skill that guides defect review and lesson capture without hidden execution or data exfiltration behavior.

Install if you want a Chinese-language QA retrospective template and workflow. Be aware that broad trigger words may activate it for generic “summary” requests, so clarify that you want a QA retrospective when using it.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation rule is broad enough that common terms like '总结' or '经验沉淀' could invoke the skill outside a clearly bounded QA retrospective context. Unintended activation can cause the agent to apply the wrong workflow, mishandle user intent, or expose internal process guidance in irrelevant contexts, though it does not directly enable code execution or data exfiltration.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill metadata and body are written as Chinese-only operational guidance, with no stated option to adapt to the user's language. This can cause unsafe or incorrect handling when users operate in another language, increasing misunderstanding risk and making downstream outputs less reliable, but it is primarily a usability and policy-boundary issue rather than a direct security exploit.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal