lynx-web-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill fetches and saves content from arbitrary external websites, creating a surface for indirect prompt injection where malicious instructions on a webpage could influence the agent's next actions.
  • Ingestion points: Data retrieved from search engines (Google, Brave, etc.) and arbitrary URLs via lynx in SKILL.md.
  • Boundary markers: Absent; retrieved content is saved as raw text or HTML directly to /tmp without delimiters or safety warnings for the agent.
  • Capability inventory: The skill uses lynx for network requests and python for string processing; it writes output files to the /tmp directory.
  • Sanitization: The skill correctly uses urllib.parse.quote_plus to sanitize search queries, but it does not perform any sanitization or filtering on the content fetched from the web before saving it.
  • Command Execution (SAFE): The skill executes standard system commands (lynx, python, tee). The provided scripts use proper variable quoting to prevent simple command injection from user-provided queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 09:58 PM