stashr

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @stashr/cli Node.js package using npm or bun to enable CLI-based transport for library management.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the library, including searching, fetching content, and downloading media to specified local paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from bookmarked URLs and private library entries, creating a surface for injection attacks.
  • Ingestion points: The fetch, fetch_many, and search tools (MCP) and stashr get and stashr search commands (CLI) retrieve external data from the Stashr library.
  • Boundary markers: The instructions recommend inlining content as Markdown but do not specify the use of clear delimiters or instructions to ignore embedded commands within that content.
  • Capability inventory: The skill has the ability to write media to the file system via the stashr media command and perform network operations to synchronize with the Stashr service.
  • Sanitization: No specific sanitization or filtering logic is mentioned for the content retrieved from saved bookmarks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 06:28 AM