ClawHub
Back to skill

Security audit

Product Marketing Context

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a reusable product marketing context file from user-provided input or repository marketing materials, and its file access is disclosed and aligned with that purpose.

Before installing, be aware that the skill may read product and marketing files in the current repository to draft context and will create or update `.claude/product-marketing-context.md`; review the generated document before allowing it to be saved because other marketing skills may reuse it later.

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
96% confidence
Finding
The skill metadata uses broad trigger phrases such as 'product context,' 'marketing context,' 'set up context,' and 'positioning,' which can match many ordinary conversations and cause the skill to activate when the user did not explicitly request it. Because this skill reads across the repo and writes a shared context file, unintended invocation can lead to unnecessary data collection, incorrect summaries, or unwanted file modification.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to save content to `.claude/product-marketing-context.md`, but the skill description does not clearly warn users up front that it will create or overwrite a workspace file. Users may invoke the skill expecting conversation-only assistance, and an unexpected write operation can overwrite prior context or persist inaccurate information that other skills later trust.

Static analysis

No suspicious patterns detected.