investigate-ai-session
Warn
Audited by Snyk on Aug 29, 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 AI agent session transcripts and conversation histories via Amplitude analytics tools, which contain user-submitted inputs and prompts from external end-users interacting with the monitored agents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata