omni-sync-cloud
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
curlcommand to interact with a local service athttps://localhost:20128. These commands are used to authenticate with cloud workers, update credentials, resolve models, and manage synchronization bundles and tokens. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local API endpoints, which represents a potential attack surface if the synchronized data from cloud storage contains malicious instructions.
- Ingestion points: Data is retrieved from endpoints such as
/api/sync/bundle,/api/sync/tokens, and/api/cloud/models/aliasviaGETrequests. - Boundary markers: The skill does not implement delimiters or instructions to ignore potential commands embedded within the retrieved data.
- Capability inventory: The skill executes shell commands (
curl) for network communication and data management. - Sanitization: No explicit validation or sanitization of the responses from the API is described in the provided skill instructions.
Audit Metadata