AI-Assisted Secure Coding (Appendix C) · AI Code-Review & Assistant Bot Hardening
Lock review bot prompts and policy
Verify that AI review and assistant bot system prompts and policy configurations are integrity-checked at load time (signed, hash-pinned), and that nothing in the repository, in branch contents, in PR-sourced environment variables, or in any other user-controllable input can modify them.
OWASP AISVS v1.01, requirement AC.11.2
In plain English
Check bot system prompts and policy configuration for integrity when they load, and make sure nothing in the repository, branches, PR environment variables or other user-controlled input can change them.
What good looks like
- Prompts and policies are signed or hash-pinned.
- They load from a location contributors cannot change.
- Integrity failures stop the bot.
How teams usually do it
- Storing bot configuration in a protected repository with pinned versions.
Evidence an auditor would accept
- Configuration location and integrity checks.
Common mistakes
- Reading bot instructions from a file in the PR branch.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.