od-next-media-inputs
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes vendor-specific CLI tools using environment variables such as $OD_BIN and $OD_NODE_BIN to perform media search and download operations. This is a standard integration for the nexu-io vendor ecosystem.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data when reading titles and alt text from web search results to select appropriate assets. 1. Ingestion points: Metadata from web/image search results (titles, alt text). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided. 3. Capability inventory: The skill has the ability to execute the vendor CLI tool and write files (images and sidecar metadata) to the local assets directory. 4. Sanitization: The instructions do not specify any validation or sanitization for the ingested web metadata.
Audit Metadata