browser-automation
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for web scraping and browser automation, which creates an attack surface for indirect prompt injection. Malicious instructions embedded in scraped web content could potentially influence the agent's behavior.
- Ingestion points: External web pages and DOM content accessed via automation tools (SKILL.md).
- Boundary markers: No delimiters or specific instructions to ignore embedded content are provided.
- Capability inventory: Broad browser navigation and data extraction capabilities using Playwright and Puppeteer.
- Sanitization: No sanitization or validation of the retrieved content is mentioned.
Audit Metadata