Add Trustabl Agent Scanner to CI

[kathrina-trustabl]

We came across your repo and we like how you are developing a local-first regression and provenance SDK for AI agents to record behavior and detect reasoning drift. We scanned the repo, and noticed agent runtime reliability findings that might be worth reviewing.

1. [LOW] CrewAI agent has no explicit max_iter limit
   File: tests/integrations/test_crewai.py
   What it means: This Agent sets no explicit max_iter, so it falls back to CrewAI's default iteration cap (documented as 20).

Recommendations are based on our understanding of agent runtime reliability, some findings may be intentional. Please let us know if this was intentional or if our findings are helpful so we can improve the accuracy of the scanner.

Best,
Trustabl.ai
Open-source AI agent reliability scanner (runs locally, GitHub Action)

[Therealdk8890]

Thanks for the PR and for flagging this. The max_iter finding was useful. This is an offline CrewAI integration test, but explicitly bounding the iterations makes the test more deterministic, so I added max_iter=2.

I also made a few hardening changes to the proposed workflow: explicitly disabled Trustabl telemetry, removed the unnecessary pull-requests: write permission, disabled PR comments/artifact uploads, and kept SARIF reporting enabled.

I appreciate you taking the time to scan the project and open the contribution.