
Audits GitHub Actions workflows that run AI coding agents for prompt injection risks
- Open source
- 8.2K GitHub stars
- AI models and LLM tooling


Audits GitHub Actions workflows that run AI coding agents for prompt injection risks

Guides an agent through a security-focused review of PR, commit or diff changes

Adds evidence checks and a quality gate to security audits so findings are not suppressed

Has the agent review a codebase for security flaws, secrets and vulnerable dependencies

Adds policy checks, intent screening, trust scores and audit logs to AI agents

Builds a verified map of an unfamiliar codebase before any bug hunting begins

Audits an AI agent codebase against the OWASP ASI Top 10 agentic security risks

Independently re-runs a supplied proof-of-concept against before and after builds

Runs a multi-agent security review of native C/C++ code for memory and race bugs

Judges whether reproduction evidence proves a new regression or an exclusion

Reviews GitHub Actions workflows for injection, privileged triggers and token scope risks

Checks code against its specification to find requirements it breaks or omits
The closest alternatives to Verify agent action are Agentic actions auditor, Differential review, Audit integrity, Security review and Agent governance.
Yes. Agentic actions auditor, Differential review, Audit integrity have a free or open-source option.