upload
Warn
Audited by Snyk on Jun 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime reads outsider-authored free text from a user-selected or auto-discovered session transcript JSONL (e.g.,
~/.claude/projects/.../*.jsonlor~/.cursor/projects/.../agent-transcripts/*.jsonl), parses each JSON line, and sends the resulting text content into the LLM context via the agent’s upload flow (indirect prompt injection risk from transcript contents).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata