compliance-legal
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted marketing materials, creating an ingestion point for indirect prompt injection. However, the lack of dangerous tools or capabilities limits the potential impact. Evidence: 1. Ingestion points: Marketing materials, data handling practices, and advertising campaigns. 2. Boundary markers: Absent. 3. Capability inventory: None (text-only prompt). 4. Sanitization: None.
- [Prompt Injection] (SAFE): No direct injection or bypass patterns were detected.
- [No Code] (SAFE): No executable code, remote downloads, or dependencies are present in this skill.
Audit Metadata