mirantis
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage via NPM. This is a vendor-owned tool frommembranedevused to facilitate the integration. - [COMMAND_EXECUTION]: The skill relies on shell commands via the
membraneCLI to perform core functions, such asmembrane login,membrane connect, andmembrane action run. These commands are standard for this platform's integration pattern. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes data retrieved from the Mirantis environment.
- Ingestion points: External data enters the context via the output of the
membrane action runcommand. - Boundary markers: There are no explicit delimiters or boundary markers specified in the instructions for the ingested data.
- Capability inventory: The skill possesses command execution capabilities through the CLI tool (e.g.,
membrane action create). - Sanitization: No specific sanitization or filtering of external data content is documented in the instructions.
Audit Metadata