tool-extension

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly lists Brave Search and GitHub as available MCP servers, which indicates the skill fetches and ingests open/public third-party content (search results and public repo data) that the agent would read and could materially influence its decisions or tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 09:08 PM