ory

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the Membrane CLI tool via npm install -g @membranehq/cli@latest and uses npx for command execution. This is standard setup for the vendor's integration platform.
  • [COMMAND_EXECUTION]: The skill relies on shell commands (membrane and npx) to manage authentication, establish connections to ORY, and run specific API actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from the ORY API via the Membrane CLI, creating a surface for potential indirect instructions in data.
  • Ingestion points: Output from membrane action run and membrane connection get commands in SKILL.md.
  • Boundary markers: Absent; the skill does not specify delimiters for tool output.
  • Capability inventory: Shell command execution and network requests via the membrane CLI.
  • Sanitization: Absent; the skill instructions do not mention explicit sanitization of external API data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 02:54 PM