pp-withings

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the withings-pp-cli and withings-pp-mcp tools from the vendor's GitHub repository and npm registry as part of the installation process.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to install dependencies, synchronize health data, and perform analytics using the installed binary.
  • [DATA_EXFILTRATION]: The skill provides a --deliver webhook flag that allows routing health data to external URLs, and the feedback command can send local notes to a remote endpoint if configured.
  • [PROMPT_INJECTION]: The skill implements a digest feature for LLM ingestion, creating a potential surface for indirect prompt injection from health data sources.
  • Ingestion points: Withings API health metrics and user-provided notes in blood pressure reports (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers for the digest output are described in the skill instructions.
  • Capability inventory: The skill can write files, send data to webhooks, and execute commands using the provided CLI tool.
  • Sanitization: No sanitization of the health data or user notes is described before the data is prepared for agent consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 04:30 PM
Security Audit — agent-trust-hub — pp-withings