setup

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill manages the installation of several Python packages associated with the Pipecat ecosystem, specifically pipecat-ai[cli], pipecat-ai-context-hub, and pipecatcloud. These are official resources used to provision the requested development environment and are installed via the uv tool or pip only after explicit user approval.
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to verify the state of the execution environment, check tool versions, and perform indexing operations. Examples include pipecat --version, uv tool install, and PCH status checks. The instructions include guardrails to prevent accidental destructive actions, such as avoiding --force or --reset-index flags during initial setup.
  • [DATA_EXFILTRATION]: The skill handles authentication for Pipecat Cloud services. It includes defensive measures to prevent sensitive information like PIPECAT_TOKEN or raw API responses from being exposed to the AI's context. It mandates the use of a local wrapper script (scripts/safe_cloud_metadata.py) that filters and validates organization metadata, ensuring only schema-compliant, non-sensitive identifiers are returned to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 08:34 AM