ads-generate
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection.
- Ingestion points: The skill reads
campaign-brief.mdandbrand-profile.jsonto generate image prompts and instructions for sub-agents. - Boundary markers: No explicit delimiters or boundary markers are defined to isolate the external content from the system instructions.
- Capability inventory: The skill has the ability to spawn sub-agents (
visual-designer,format-adapter), execute commands via thebanana-claudeCLI, and write generated assets to the local filesystem (./ad-assets/). - Sanitization: The instructions do not describe any sanitization, validation, or escaping of the data ingested from the campaign brief before it is processed by the agent or sub-agents.
Audit Metadata