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