bluemind-ghost-notifications
Warn
Audited by Snyk on Mar 28, 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 explicitly requires querying a user-supplied BlueMind instance (collecting "URL of the instance BlueMind" and API key in SKILL.md) and the references/api-endpoints.md shows curl calls (e.g., POST /calendars/_search, GET /calendars/{container}/{uid}/complete, /_list) whose returned, untrusted event data the agent is expected to read and use to decide remediation, so it ingests and acts on third‑party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata