geoapify
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/clipackage globally via npm, which is a verified tool belonging to the vendor. - [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform geocoding and routing tasks, which is the intended functionality for this integration. - [PROMPT_INJECTION]: The skill processes external API data, creating a surface for indirect prompt injection. 1. Ingestion points: API responses from
membrane action runandmembrane requestcommands. 2. Boundary markers: Absent. 3. Capability inventory: Command execution via the CLI. 4. Sanitization: No sanitization logic is described for API data before it enters the agent context.
Audit Metadata