social-measurement-loop
Warn
Audited by Snyk on Aug 20, 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). In SKILL.md, the runtime workflow “Reads” untrusted, user-exported native analytics/screenshots and also ingests open-surface community data via the connector
discourse.py(public forum JSON) in “Community-health mode on our Discourse forum,” meaning outsider-authored free text can be ingested into the LLM via those connector outputs without first selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata