moai-alfred-context-budget

Warn

Audited by Snyk on Mar 1, 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). SKILL.md Pattern 4 (MCP Server Optimization) and the .claude/mcp.json examples explicitly instruct enabling MCP servers such as "context7" and "github" for documentation research and GitHub API access, which causes the agent to fetch and ingest public third‑party (user‑generated) content that can influence tool use and workflow decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:06 AM