github-code-scanning

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

Offline agent and CI permission-risk auditor with Markdown, JSON, CSV, SARIF, Code Scanning, rules config, and CI gates.

Offline linter for AGENTS.md, CLAUDE.md, CODEX.md, Cursor rules, and AI agent runbooks, with SARIF, JUnit, CI gates, and Code Scanning support.

Offline test evidence gap mapper for AI coding agent changes with Markdown, JSON, JUnit, SARIF, coverage, and CI gates.

Offline prompt-change auditor for LLM apps and coding agents, with variable contracts, diff risk checks, redaction, SARIF, JUnit, and CI gates.

Offline redaction and reviewable context-pack CLI for AI coding agents, with Markdown, JSON, SARIF, CI gates, and Code Scanning support.

Reachability-aware CVE prioritizer: tells you which vulnerabilities are actually reachable from your code, and drafts the GitHub issue for the ones that matter.