data-expert

Warn

Audited by Snyk on May 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's workflow and scripts (SKILL.md and scripts/export_conversations.py / scripts/fetch.py) explicitly fetch full conversation detail and message history (GET /projects/{pid}/conversations and GET /projects/{pid}/conversations/{cid}) and KB citations — i.e., user-generated customer messages and external KB content are ingested and read as part of analysis, so untrusted third-party content can influence downstream decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 7, 2026, 03:17 AM
Issues
1