Version updated for https://github.com/Acacian/aegis to version v0.9.4. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agent-Aegis is a governance layer for AI agents that provides a unified runtime to standardize and enforce essential governance features such as prompt-injection blocking, PII masking, policy enforcement, trust delegation, and tamper-evident auditing across 12 popular AI frameworks. It simplifies the implementation of these governance primitives by auto-instrumenting existing agent frameworks without requiring code changes, enabling developers to ensure compliance and security while reducing complexity. The action addresses challenges like inconsistent governance implementations and enhances trust, transparency, and control in AI-driven systems.

Version updated for https://github.com/Acacian/aegis to version v0.9.2. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agent-Aegis is a GitHub Action designed to identify and mitigate ungoverned AI and tool calls in your codebase, helping developers ensure compliance with governance policies before deploying to production. It scans code to detect risky patterns across multiple frameworks, such as unregulated API calls, data leakage, and uncontrolled code execution, and provides automated solutions to fix these issues. By adding a single line of code, it enables features like policy enforcement, PII masking, injection blocking, and audit trail generation without requiring manual code modifications.

Version updated for https://github.com/Acacian/aegis to version v0.9.1. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Aegis is a runtime security tool for AI agents that provides automated guardrails, governance, and auditing without requiring code changes. It integrates with 11 popular AI frameworks to monitor and secure actions such as prompt injection detection, PII masking, and selection-by-negation governance, ensuring compliance and safety in AI operations. By offering features like “aegis plan” for policy previews, regression testing, and CI/CD gating, it automates policy enforcement and enhances the security and reliability of AI agent deployments.