gui-tools

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md "Tip for AI Agents" explicitly tells the agent to use MCPs/web_search (e.g., perplexity, firecrawl, ref) to fetch vendor pricing and documentation pages such as the GitKraken pricing or official vendor docs—public third‑party web content the agent is expected to read and use to influence recommendations.