insomnia
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the "@membranehq/cli" package from the official npm registry. This is a vendor-owned tool required for the skill's core functionality, including authentication and API proxying.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Insomnia API client, which introduces a potential surface for indirect prompt injection from external API responses.
- Ingestion points: API data returned by the "membrane action run" and "membrane request" commands.
- Boundary markers: The skill instructs the agent to use the "--json" flag for all commands to ensure output is handled as structured data rather than unstructured text.
- Capability inventory: The skill can execute CLI commands, perform authenticated network requests through the Membrane proxy, and manage external service connections.
- Sanitization: The skill relies on structured JSON output for data processing; no explicit sanitization or filtering of the external API content is defined within the markdown instructions.
Audit Metadata