kong
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from npm and usesnpxto execute commands. These resources are provided by the official vendor to facilitate the integration.- [COMMAND_EXECUTION]: Uses themembranecommand-line utility for authentication, connection establishment, and API interaction. These commands are typical for CLI-based service management.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading data from external Kong API endpoints, which represents a potential ingestion surface for third-party content. - Ingestion points: Data returned from Kong via the
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters or "ignore instructions" warnings are included in the provided documentation.
- Capability inventory: The agent can list/run Kong actions and send raw HTTP requests (GET, POST, etc.) using the CLI.
- Sanitization: Predefined actions use an
inputSchemaandoutputSchemato structure data, though raw requests bypass these schemas.
Audit Metadata