init-first-agent
Warn
Audited by Snyk on Aug 30, 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 prompts the operator to send a DM to the bot so it can query local database logs in step 3a (
messaging_groupstable), which can contain outsider-authored free text depending on who messages the bot.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata