jupiterone
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage, which is the official command-line tool provided by the vendor for platform interaction. - [COMMAND_EXECUTION]: Instructs the agent to use the
membraneCLI for managing connections and executing actions against the JupiterOne API. These commands are localized to the platform's ecosystem and used for intended integration logic. - [PROMPT_INJECTION]: The skill processes external data from JupiterOne assets and API responses, creating a surface for indirect prompt injection.
- Ingestion points: Data retrieved via
membrane action runandmembrane requestcommands. - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: Execution of
membraneCLI commands via the shell. - Sanitization: No explicit sanitization or validation of the external data content is described in the skill instructions.
Audit Metadata