ovstorage-user-list-and-paginate
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a standard technical guide for storage enumeration. It provides instructions on handling pagination tokens and managing memory usage when listing large directories.
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from external storage backends. This creates an attack surface for indirect prompt injection if the storage contains objects with malicious filenames or metadata designed to influence agent behavior.
- Ingestion points: Data retrieved via the
ovstorage_listtool as described inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in object metadata.
- Capability inventory: The skill facilitates listing (
ovstorage_list) and references reading operations (ovstorage-user-read-bytes). - Sanitization: There is no mention of sanitizing or validating the content of the listed items before they are added to the agent's context.
Audit Metadata