aiox-architect
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required activation path reads only local, owner-controlled data (git status,
.aiox/handoffs, story files), but the skill also lists exa (web search) and context7 (library docs) as research tools, which the agent actively queries for technology evaluation, so outsider-authored web content is reachable only after the agent searches for it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata