skills/casemark/skills/vaults/Gen Agent Trust Hub

vaults

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the casedev CLI to manage document vaults, including operations for creating vaults, uploading files, and performing semantic searches. These commands are integral to the skill's function and operate within the context of the vendor's tools.
  • [PROMPT_INJECTION]: The skill processes external documents for storage and search, which introduces a surface for indirect prompt injection. This is a functional requirement of the document management feature.
  • Ingestion points: Document content is ingested via casedev vault object upload and casedev vault upload in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
  • Capability inventory: The casedev CLI tool has permissions to read from and write to the local file system.
  • Sanitization: There is no mention of content sanitization or validation before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:56 PM