claude-code-guide

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly lists "web access" under Tools (references/core/tools.md) and describes MCP servers for connecting to external APIs like GitHub and Jira (references/configuration/mcp.md), meaning the agent can fetch and read public/user-generated third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:32 AM