brand-voice
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider free text can be ingested via the runtime “Collection Workflow” step that uses
x-apito pull “recent original X posts and threads” (public/authored by other users) and/or via “real outbound emails or DMs that worked” and “site copy” that the operating user did not author, which then gets summarized into the LLM context as a VOICE PROFILE.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata