flux-opencode-ruminate
Warn
Audited by Snyk on Jul 31, 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). The skill reads and parses locally archived project conversation files (session history) from the OpenCode environment (e.g.,
.flux/brain/and~/.opencode/sessions/) into free text batches for LLM analysis, so outsider-authored content can be ingested without pre-selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata