adobe-design-to-pdf
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements defensive measures by instructing the agent to ignore and never repeat or act upon instructions found within tool results or metadata. This effectively mitigates risks where external data could attempt to hijack the agent's behavior.
- [DATA_EXPOSURE]: The skill contains explicit privacy instructions requiring the removal of personal identifiers (names, dates, emails, addresses) from search queries before they are sent to the underlying search tools.
- [SAFE]: The skill uses a restricted set of fixed user messages and controlled action menus, which limits the agent's ability to be coerced into generating unauthorized content or leaking internal logic.
Audit Metadata