pp-withings
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions require the user to install the
withings-pp-clibinary usingnpx -y @mvanhorn/printing-press-libraryorgo install github.com/mvanhorn/printing-press-library/library/devices/withings/cmd/withings-pp-cli@latest. These resources are hosted under the author's own GitHub account and NPM scope. - [DATA_EXFILTRATION]: The CLI tool includes a
--deliver webhook:<url>feature that allows the agent to POST command results to an external URL. Additionally, the tool features a feedback mechanism that can transmit locally stored logs to a remote endpoint if theWITHINGS_FEEDBACK_ENDPOINTenvironment variable is set. - [COMMAND_EXECUTION]: The skill operates by executing the
withings-pp-clibinary via shell commands, utilizing arguments provided by the agent to perform health data analysis. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests external health data (from the Withings API) that is subsequently processed by the agent. Ingestion points: Withings health metrics retrieved via API. Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the health data. Capability inventory: The skill triggers shell subprocesses via the CLI tool. Sanitization: No data sanitization or validation of API responses is documented.
Audit Metadata