withings
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from an external source (Withings API) and incorporates it into the agent's context, creating a potential surface for indirect prompt injection.
- Ingestion points: Data returned by the
withings query,withings measures,withings activity, and other CLI subcommands described inreferences/commands.md. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple backticks) to separate external data from the system prompt, nor do they include warnings to ignore instructions embedded within the fetched data.
- Capability inventory: The skill utilizes the
withingsCLI tool to execute various subcommands (query, measures, activity, heart-list, etc.) via subprocess calls. - Sanitization: There are no instructions for the agent to sanitize, escape, or validate the content of the data returned by the API before processing it.
Audit Metadata