newsletter-ad-review

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from CSV/Excel files and user-pasted tables (SKILL.md, Step 2), creating a surface for indirect prompt injection. This is a standard risk for skills that aggregate external data and is expected for the documented use case.
  • Ingestion points: External report files and pasted text.
  • Boundary markers: Not defined in the instructions.
  • Capability inventory: Internal marketing tools (get_marketing_context, list_marketing_references).
  • Sanitization: No explicit content validation or filtering described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:21 PM