temporal-python-testing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's replay-testing instructions and scripts (see resources/replay-testing.md and scripts/export_histories.py) explicitly connect to external Temporal servers (e.g., production.temporal.io) to fetch and load workflow histories — user-generated, untrusted event histories — which the agent is instructed to read and replay to drive test/replay decisions, so third‑party content can materially influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's runtime setup uses docker-compose to pull and run remote container images (e.g., temporalio/auto-setup:latest, temporalio/ui:latest, postgres:14-alpine) which are fetched at runtime and execute external code that the skill depends on.