infinity

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from NPM. This is the official CLI tool for the Membrane platform, provided by the vendor.
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI to perform all operations, including authentication, action discovery, and data manipulation within the Infinity service.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes user-controlled data from Infinity.
  • Ingestion points: Data is ingested through membrane action run commands that fetch workspaces, boards, items, and comments from Infinity.
  • Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore potential instructions embedded within the retrieved Infinity data.
  • Capability inventory: The skill includes capabilities to read data (list workspaces, boards, items) and write data (create items, boards, folders, comments) via the same CLI interface.
  • Sanitization: The skill does not provide instructions for sanitizing or escaping content retrieved from the Infinity API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:11 AM
Security Audit — agent-trust-hub — infinity