Ad Creative Remake
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as an instructional framework for marketing agents to analyze underperforming ads and propose creative variations. It lacks executable scripts or command-line operations that could pose a direct security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process external data sources.
- Ingestion points: Performance data, product facts, claims, and original ad content (as specified in
SKILL.md). - Boundary markers: None explicitly defined to separate untrusted performance data or third-party claims from the agent's internal reasoning.
- Capability inventory: The skill uses
media.generate_video,media.edit_video,media.generate_image,media.upload_file, and hasworkspace-writepermissions. - Sanitization: There are no mentioned sanitization or validation steps for the input data before it is used to drive media generation or workspace writes.
- [NO_CODE]: There are no code files (Python, JavaScript, shell scripts) included with this skill, reducing the risk of traditional malware or exploit execution.
Audit Metadata