web-research
Warn
Audited by Snyk on Feb 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly exposes the agent to arbitrary public web content via Brave Search and page-fetching commands (e.g., "search.js ... --content" and "content.js https://example.com/article"), which pulls untrusted third-party webpages into the agent's workflow and can materially influence its actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary external pages at runtime (e.g., via ~/agent-tools/brave-search/content.js https://example.com/article) and extracts/injects that page content into the agent output/context, meaning remote content can directly control prompts.
Audit Metadata