podium-webchat-handler

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from Podium webchat widgets (e.g., data.get("body") in scripts/webchat_ingest.py). This creates a vulnerability surface where malicious instructions embedded in chat messages could be processed and forwarded to downstream CRM or agent systems.
  • [COMMAND_EXECUTION]: The skill uses Bash to execute curl, jq, and python3. These tools are used for legitimate interactions with Podium's official API endpoints (for contacts and message management) and for running its own internal management scripts.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the phonenumbers library via PyPI. This is a well-known, trusted Python package used for the skill's primary function of E.164 phone number normalization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:47 AM
Security Audit — agent-trust-hub — podium-webchat-handler