Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.74. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit automates the security auditing of AI agent pipelines by scanning and reporting on misconfigurations, hardcoded secrets, tool poisoning, and other potential vulnerabilities across 10 different platforms. Unlike hosted scanners, AgentAuditKit runs fully offline and deterministically, producing auditor-ready compliance-evidence packs that cover a wide range of security categories including EU AI Act, SOC 2, ISO 27001/42001, HIPAA, NIST AI RMF, and regional regimes.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.73. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary Summary: AgentAuditKit is a security scanner designed to scan AI agent pipelines for misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows. It runs fully offline and deterministically, ensuring consistent findings across different runs. The action provides auditor-ready compliance-evidence packs in SARIF format and PDF reports, covering 12 security frameworks.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.72. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit is a security scanner designed to audit AI agent pipelines offline and deterministically. It identifies misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 agent platforms. Unlike hosted scanners, AgentAuditKit runs fully offline without network calls, ensuring reproducibility with a 0% variance in findings across multiple runs. Additionally, it produces auditor-ready compliance-evidence packs using SARIF for GitHub Security tab and PDF reports mapped to 12 security frameworks.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.71. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit is a security scanner designed to audit MCP-connected AI agent pipelines. It automates the detection of misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 agent platforms. Unlike hosted scanners that rely on machine learning, AgentAuditKit runs fully offline and deterministically, ensuring consistent findings and compliance evidence packs with support for 12 security frameworks.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.70. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit is a security scanner designed to audit AI agent pipelines and identify misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 agent platforms. It runs fully offline and deterministically, producing auditor-ready compliance-evidence packs that include SARIF for GitHub Security tab and PDF evidence reports mapped to 12 security frameworks. The action supports 85 scanner modules including AST-based Python taint analysis and regex pattern scanners for TypeScript/JavaScript and Rust.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.69. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action is a security scanner designed to audit AI agent pipelines. It runs offline and deterministically, finds misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 agent platforms. Key capabilities include running fully offline, producing auditor-ready compliance-evidence packs, and supporting OWASP coverage for top security categories. The action provides a total of 284 rules across 12 categories, with 85 scanner modules, including AST-based Python taint analysis and regex pattern scanners for TypeScript/JavaScript and Rust.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.68. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit is a security scanner designed to audit AI agent pipelines for potential misconfigurations, hardcoded secrets, tool poisoning, and other vulnerabilities. It is the missing npm audit solution specifically tailored for AI agents, running offline and deterministically without relying on an LLM. The action produces auditor-ready compliance-evidence packs including SARIF reports and PDF evidence reports mapped to 12 security frameworks, ensuring precision and reliability in security audits.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.67. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary AgentAuditKit is a security scanner designed to audit AI agent pipelines for misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 agent platforms. It runs fully offline and deterministically, avoiding the need for network calls and ensuring consistent findings. Additionally, it produces auditor-ready compliance-evidence packs in SARIF format, covering multiple security categories and frameworks.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.66. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary Summary: AgentAuditKit is a security scanner designed to audit AI agent pipelines offline and deterministically. It identifies misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across 10 major agent platforms. Unlike hosted scanners, AgentAuditKit runs fully offline and produces auditor-ready compliance-evidence packs using SARIF for the GitHub Security tab and PDF reports mapped to 12 security frameworks, ensuring precision in detection and auditability.

Version updated for https://github.com/sattyamjjain/agent-audit-kit to version v0.3.65. This action is used across all versions by ? repositories. Action Type This is a Docker action. Go to the GitHub Marketplace to find the latest changes. Action Summary The AgentAuditKit action is a security scanner designed to audit AI agent pipelines. It ensures that your code, configs, and secrets remain secure by identifying misconfigurations, hardcoded secrets, tool poisoning, rug pulls, trust boundary violations, and tainted data flows across various platforms. Unlike hosted scanners, it runs fully offline and deterministically, producing auditor-ready compliance-evidence packs in SARIF and PDF formats for 12 security frameworks. It covers 274 rules across 10 agent platforms, including AST-based Python taint analysis and regex pattern scanners for TypeScript/JavaScript and Rust.