NYC

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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:50 PM