ecommerce-product-montage
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions.
- Ingestion points: The workflow involves gathering information from "product page or user notes" as mentioned in
SKILL.mdandreferences/proof-placement.md, as well as inventorying source assets. - Boundary markers: The skill lacks explicit instructions, delimiters, or warnings to isolate external data or to instruct the agent to disregard instructions that might be embedded within that data.
- Capability inventory: The skill utilizes
OpenChatCutediting tools to create video montage plans, structures, and sequences based on provided material. - Sanitization: There is no evidence of sanitization, validation, or filtering of external content before it is used to generate the video production plan.
Audit Metadata