Security●●Solid
Security Scanner for Agent Skills and MCP
Finally a security linter for MCP configs before you accidentally execute a prompt injection payload.
Solve My ProblemShip It
lirantal
701mo ago
Back to browse
GitHub Repository
2 starsTypeScript
Overreach – audit your AI agent's diff against the prompt you gave it
by Naveja·Jun 20, 2026·1 point·0 comments
AI Analysis
●●SolidBig BrainSolve My Problem
Deterministic diff parsing catches unauthorized deps and endpoints after LLM extracts scope.
Strengths
- •Three-stage pipeline minimizes LLM calls—only stage one uses a model
- •Catches specific violations: env vars, endpoints, cron jobs, dependencies
- •Demo mode works without API key—npx overreach-cli demo exits with findings
Weaknesses
- •AI agent oversight is getting crowded—Cursor, Continue already audit changes
- •Only 2 stars suggests limited real-world testing so far
Category
Target Audience
Developers using AI coding agents
Similar To
Cursor · Continue · Sourcegraph Cody
Similar Projects
Security●●●Banger
Kvlar – Open-source firewall for AI agent tool calls
Fail-closed MCP security policy layer with curated templates and policy-as-code YAML.
Solve My ProblemShip It
kvlar
103mo ago
AI/ML●Mid
Savile: Local-first MCP server for AI agent prompts and skills
Git-native prompt versioning with Crucible evaluation, but only 1 star on GitHub.
Niche GemShip It
mr8lu
102mo ago
Developer Tools●Mid
OpenRuna–graph-linked prompts,MCP servers and agent skills
Curated directory of 1,700+ prompts when Awesome lists already exist.
Crowd Pleaser
dcnl1980
101d ago
AI/ML●Mid
A readiness scorer for MCP servers, checked against emerging standards
Free MCP validator when official tooling doesn't exist yet.
Ship ItNiche Gem
nrengan
411d ago
Security●●Solid
OpenACA – security scanner for AI agent stacks (MCPs,skills,plugins)
SCA for agent configs when Snyk and Dependabot can't read mcp.json files.
Ship ItBold Bet
vinodkone
234d ago