faster-chrome-devtools-skill

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch and ingest arbitrary page content from OUTSIDER-controlled URLs via commands like navigate + get-text/snapshot/eval, which read the loaded page’s DOM/text into the agent’s LLM context (indirect prompt injection risk from public web content).