ClawHub
Back to skill

Security audit

Campaign Review

Security checks for vulnerabilities and agentic risk

Overview

This is a plain documentation-only skill for campaign/event review work, with some broad business-consulting language but no hidden execution, persistence, or privileged access.

Before installing, treat this as a general campaign and event review assistant. Provide only the business data needed for the specific review, and have domain experts check any compliance, risk, budget, or strategic recommendations before acting on them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata and name indicate a narrow 'campaign review' function, but the body expands into broad event planning, business operations optimization, strategic decision support, and process automation. This scope drift can cause an agent or user to rely on the skill for decisions outside its declared purpose, increasing the chance of over-collection of sensitive business data, unsafe delegation, and misuse in higher-risk operational contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description includes English text alongside the Chinese term "主持稿," implying the skill may produce output in a specific language or mixed-language format. The file does not state that users can choose their preferred output language or locale, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.