social-media-promoter

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Vulnerable to indirect prompt injection via external content ingestion. * Ingestion point: Sanity CMS content and excerpt fields defined in the input requirements and GROQ query. * Boundary markers: Absent; instructions lack clear delimiters for separating untrusted content from the system prompt. * Capability inventory: Text generation for user review (no autonomous system write/execute capabilities). * Sanitization: Absent; no content validation is performed. * Mitigation: The workflow requires manual user review before posts are finalized.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:35 PM