token-burn
Warn
Audited by Snyk on Aug 6, 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 runtime workflow runs a local script that scans
~/.claude/projects/<slug>/<session>.jsonland ingests assistantusage/aiTitle/metadata from those JSONL transcript lines, which can contain outsider-provided text from the user’s interactions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata