architecture-advisor

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's sync-references.sh explicitly clones a public GitHub repository (https://github.com/cristoslc/architecture-reference) into references/ and SKILL.md requires the agent to read and synthesize those third-party reference/catalog/evidence files (including user-generated competition submissions in the optional evidence-pool), so untrusted public content is fetched and directly influences recommendations.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 05:37 PM