amazon-location-service
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the
@membranehq/clipackage from the public NPM registry. This is the official command-line interface provided by the vendor (membranedev) for interacting with their service.- [COMMAND_EXECUTION]: The skill executes shell commands using themembraneCLI to authenticate users, establish service connections, and run location-based actions.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external service outputs. - Ingestion points: Data retrieved from
membrane action list,membrane action get, andmembrane action runcommands inSKILL.md. - Boundary markers: Absent; the skill does not use delimiters or provide instructions to ignore commands within the returned data.
- Capability inventory: The skill can create and execute arbitrary remote actions via the
membraneCLI. - Sanitization: None; the skill does not specify any filtering or validation for the content returned by external actions.
Audit Metadata