agent-repo-architect

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). The skill explicitly performs public GitHub queries and repository scraping (mcp__github__search_repositories and the gh search used to populate ARCH_PATTERNS) and therefore ingests untrusted, user-generated repository content for analysis.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:40 PM