generate-mixed-media
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions or attempts to override agent behavior were detected in the text.
- [Indirect Prompt Injection] (SAFE): The skill defines a workflow for processing ad copy which is a potential ingestion point for untrusted data. However, as the skill provides no executable tools or scripts, there is no capability for this data to perform malicious actions. 1. Ingestion points: adCopy object in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: No scripts or tool implementations provided. 4. Sanitization: None mentioned.
- [No Code] (SAFE): The skill is documentation-only and does not include any Python, Node.js, or shell scripts.
Audit Metadata