gologin-web-access-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly requires confirming or asking the user for GOLOGIN_WEB_UNLOCKER_API_KEY and GOLOGIN_TOKEN and documents a CLI flag (--web-unlocker-api-key) for configuring them, which encourages soliciting and embedding secrets into setup/commands instead of keeping them only in environment/config, creating a clear risk of verbatim secret handling.

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests arbitrary public third‑party webpages (e.g., commands like read_page, scrape_markdown, scrape_text, scrape_json, search_web, crawl_site, batch_scrape in SKILL.md and tools.md that call the gologin-web-access CLI) and instructs the agent to read/interpret those results and escalate actions based on them, so untrusted web content can materially influence tool selection and next actions.