oura-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions involve running
npx @yasuakiomokawa/oura-mcp configure. This facilitates the download and execution of the vendor's Model Context Protocol (MCP) server package from the NPM registry. - [COMMAND_EXECUTION]: The skill requires the user to execute a terminal command (
npx) for initial OAuth configuration, which is a standard procedure for setting up the Oura Ring API connection. - [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from the Oura API (e.g., user-entered tags, notes, or metadata associated with health metrics).
- Ingestion points: API data retrieved via the
oura_api_gettool is processed across all files in therecipes/directory. - Boundary markers: The instructions do not explicitly include delimiters or 'ignore embedded instructions' warnings for the data returned by the API.
- Capability inventory: The skill's toolset is restricted to Oura API operations (
oura_authenticate,oura_api_get, etc.) and does not include capabilities for filesystem access, arbitrary shell execution, or general network exfiltration. - Sanitization: There are no explicit instructions for sanitizing or escaping content fetched from the API before processing it.
Audit Metadata