context-master
Warn
Audited by Snyk on Feb 15, 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). This skill explicitly grants subagents the "web_search" and "search" tools (see scripts/create_subagent.py SUBAGENT_TEMPLATES and generated .claude agent configs) and instructs those subagents to search and analyze external documentation/web content, so the agent will fetch and interpret open/public third-party content (potentially untrusted/user-generated) as part of its workflow.
Audit Metadata