google-cloud
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the npm registry. This is a vendor-provided tool from the author's ecosystem used to facilitate secure communication with the Membrane platform and Google Cloud services. - [COMMAND_EXECUTION]: The skill instructions involve executing various shell commands using the
membraneCLI to handle authentication, connection management, action discovery, and the execution of API requests. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external Google Cloud API endpoints, which represents a potential surface for indirect prompt injection.
- Ingestion points: Output from
membrane action runandmembrane requestcommands is read into the agent's context (SKILL.md). - Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore or isolate potentially malicious instructions embedded within the retrieved data.
- Capability inventory: The skill uses the
membraneCLI to execute arbitrary API requests, run pre-built actions, and manage cloud connections. - Sanitization: The instructions do not include steps for validating or sanitizing the content of API responses before the agent processes them.
Audit Metadata