skillopt-sleep
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text is ingested via the runtime “Harvest” step that reads past Claude Code sessions and history from
~/.claude/projects/*/<session>.jsonland~/.claude/history.jsonl, which can contain user- or third-party-authored transcript text that the agent then uses for replay/consolidation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata