agency-autonomous-optimization-architect
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md defines a workflow that runs “Shadow Traffic” on “real user data”/“serviceTask” via provider.executeWithTimeout, so outsider-authored text can be ingested through the monitored user/task inputs at runtime without requiring prior selection of specific content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata