monarch-database
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow calls Monarch API endpoints (e.g.,
/association/all,/entity/{hpo_id},/search) and ingests the returned JSON fields (names/descriptions/association items) into the agent’s LLM context; these responses are outsider-authored public web data from Monarch’s aggregated knowledgebase.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata