web-scraper

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process untrusted data from external websites, creating a surface for indirect prompt injection.
  • Ingestion points: External data enters the agent's context through HTTP requests (requests.get) and browser automation (playwright.chromium.launch, page.goto) as described in the Core Capabilities and templates in SKILL.md.
  • Boundary markers: The skill does not explicitly define boundary markers or 'ignore embedded instructions' prompts when processing scraped content.
  • Capability inventory: The skill possesses capabilities to execute network operations, automate browser actions, and parse DOM structures using BeautifulSoup and playwright (referenced in SKILL.md).
  • Sanitization: There are no specific instructions for sanitizing or filtering extracted text before it is presented to the agent for structured data extraction or analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:55 AM
Security Audit — agent-trust-hub — web-scraper