hyperise
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the
@membranehq/clipackage globally via npm, which is the official tool for the Membrane platform. - [COMMAND_EXECUTION]: Uses the
membranecommand-line utility for authentication, connecting to Hyperise, and running actions. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data from the Hyperise API.
- Ingestion points: External data enters the agent context through the output of
membrane action runandmembrane action listcommands. - Boundary markers: The instructions do not use delimiters or boundary markers to isolate data returned from the API.
- Capability inventory: The skill allows the agent to execute shell commands using the
membraneCLI to interact with external services. - Sanitization: There are no instructions provided for sanitizing or validating data retrieved from the API before it is processed.
Audit Metadata