ads-photoshoot
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses local files such as
brand-profile.jsonand~/.banana/costs.jsonto customize image generation and provide cost estimates to the user. This access is consistent with the skill's documented functionality and occurs within the local environment without evidence of external data transmission. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it interpolates user-supplied descriptions and local brand configuration data directly into image generation prompts.
- Ingestion points:
brand-profile.json(local file), user-provided product descriptions, and product URLs. - Boundary markers: The prompt templates do not utilize explicit delimiters or instructions to ignore potential commands embedded within the input data.
- Capability inventory: The skill invokes the
/banana generatetool to create images and writes files to the./product-photos/directory. - Sanitization: No specific sanitization or validation logic is applied to the input strings before they are used in prompt construction.
Audit Metadata