ad-creative
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The overall skill structure and scripts perform only the documented tasks and follow best practices for secret management.
- [EXTERNAL_DOWNLOADS]: The
scripts/run.pyscript makes network requests tohttps://ai-skills.aito process ad content. This domain belongs to the skill vendor and represents official functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content, which represents a potential attack surface for indirect prompt injection. 1. Ingestion points: The
materialText,materialFile, andmaterialUrlfields inreferences/form-schema.json. 2. Boundary markers: No explicit delimiters or safety instructions are defined in the prompt context. 3. Capability inventory: The tool is limited to sending data to the vendor API and lacks local file-write or shell-execution permissions. 4. Sanitization: Input content is not filtered or escaped before being processed by the agent.
Audit Metadata