botpenguin
Warn
Audited by Snyk on Apr 22, 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 SKILL.md shows the agent fetching user-generated BotPenguin content via the Membrane connector (e.g., "List Chats", "List Inbox Users" and proxy requests), so the agent would read third‑party chat/inbox messages that could contain instructions influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata