sendo-dev

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official @membranehq/cli package from the global NPM registry, which is an expected dependency for this vendor.
  • [COMMAND_EXECUTION]: Instructs the agent to execute shell commands using the membrane CLI to manage connections, discover actions, and run integration logic.
  • [PROMPT_INJECTION]: The skill processes untrusted user input to search for or generate new actions, creating an indirect prompt injection surface.
  • Ingestion points: User-provided values for the --intent and action description parameters.
  • Boundary markers: No delimiters or warnings are provided to prevent the agent from obeying instructions embedded in the user strings.
  • Capability inventory: The skill has the ability to execute shell commands, perform network operations, and dynamically generate and run new actions via the CLI.
  • Sanitization: No explicit sanitization or validation of user-provided strings is defined in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 11:42 AM