ClawHub
Back to skill

Security audit

中东冲突报道

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Iran conflict news-briefing template with disclosed sourcing and verification instructions, and it does not install code, persist data, or request privileged access.

Before installing, understand that this skill is meant for fast conflict updates and should be checked against cited sources, especially for casualty, damage, or escalation claims. Ask for your preferred language if you do not want Chinese output.

A.I.G

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

SkillSpector

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 skill description uses broad activation criteria such as requests for conflict updates, battle damage tracking, claim verification, and rapid briefs, which can cause the agent to invoke this skill in loosely related contexts without clear user intent. Over-broad routing increases the chance of inappropriate activation for sensitive geopolitical queries, causing misleading outputs, scope creep, or failure to apply safer, more context-appropriate handling.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill forces Chinese output by default unless the user asks otherwise, which overrides likely user language expectations and can produce inaccessible or misleading responses. In a high-stakes conflict-briefing context, unexpected language switching may impair comprehension, verification, and safe decision-making by users who did not request Chinese.

Static analysis

No suspicious patterns detected.