insomnia
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSOBFUSCATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting data from external API responses and gRPC server reflection. This creates a theoretical attack surface for indirect prompt injection, though it is standard for the tool's primary purpose. 1. Ingestion points: API response bodies via template tags and gRPC server reflection. 2. Boundary markers: None specified to distinguish between data and potential instructions. 3. Capability inventory: Shell command execution via the inso CLI. 4. Sanitization: No explicit sanitization of ingested response data is described.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the official insomnia-inso package from the npm registry for CI/CD automation.
- [OBFUSCATION]: A Base64-encoded string (JC5hY2Nlc3NfdG9rZW4=) is used within an Insomnia template tag. This decodes to a standard JSONPath expression ($.access_token) used for data extraction and is a native feature of the tool's template syntax.
Audit Metadata