silent-product-demo
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest external data from application interfaces and UI source code, creating a surface where malicious instructions could be embedded in the source material. * Ingestion points: The instructions call for capturing real application states and UI source code (SKILL.md). * Boundary markers: There are no instructions for using delimiters or boundary markers to isolate ingested content from the agent's instructions. * Capability inventory: The skill describes creative tasks like rendering and motion direction but does not define or request shell execution, network access, or file-system write tools within the analyzed file. * Sanitization: The skill lacks instructions for validating or sanitizing the ingested UI data.
- [NO_CODE]: The skill consists entirely of natural language instructions for the agent and does not provide any scripts, binary files, or automated configuration.
Audit Metadata