audit-transcripts-for-learnings
Warn
Audited by Snyk on Oct 8, 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 workflow reads past Claude Code session transcripts from local project directories (
~/.claude/projects/), which contain user and assistant messages including past inputs, potentially exposing the agent to untrusted external text injected into past sessions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata