brand-profile
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md:41-48 describes reading “website, social handles, or existing posts” and “pasted documents” as data, which at runtime can ingest outsider-authored free text (e.g., public web pages or user-provided third-party content) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata