ovstorage-user-connect-via-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for registering the ovstorage-mcp binary as a server command. This is the standard procedure for configuring MCP stdio servers and is central to the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents tools that ingest data from external storage backends, creating a potential surface for indirect prompt injection if those backends contain malicious instructions.
  • Ingestion points: Data is ingested through the ovstorage_read and ovstorage_list tools as described in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are documented in this configuration guide.
  • Capability inventory: The interface includes high-privilege storage operations such as ovstorage_write, ovstorage_delete, ovstorage_move, and ovstorage_materialize (which creates file leases).
  • Sanitization: There are no documented sanitization or validation steps for the retrieved storage data within this integration guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:50 PM
Security Audit — agent-trust-hub — ovstorage-user-connect-via-mcp