Skip to content
View pedronavarro-labs's full-sized avatar

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report pedronavarro-labs

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pedronavarro-labs/README.md

Hi, I’m Pedro

I build local-first tools for secure AI agents and integrations. I care about making permissions, tool actions and evidence understandable enough to review in a pull request.

Projects

  • AgentProof — An experimental Agent Assurance Manifest, MCP configuration scanner, ten policy checks and a GitHub Action. Try the alpha or challenge the RFC with a synthetic case. Static checks are not a security certification.
  • ScopeLens — Review whether granted GitHub App and MCP access matches an agent’s task, with a reproducible before/after demo.
  • AgentReplay — Reproduce integration failures such as uncertain writes, duplicate actions and permission denials in a local test lab.

I welcome specific, reproducible feedback and synthetic fixtures. Each project documents its limits and has a contribution path.

Español: Desarrollo herramientas abiertas para revisar permisos, probar integraciones y mejorar la seguridad de agentes de IA. Si tienes un caso reproducible sin datos sensibles, me encantará estudiarlo.

Pinned Loading

  1. agentreplay agentreplay Public

    Reproducible integration failures for AI agents. Local simulations, MCP tools and evidence-based reports.

    Python 1

  2. scopelens scopelens Public

    Your agent needs to read code. Why can it write? Evidence-aware GitHub permission reviews and static MCP configuration checks.

    Python 1

  3. agentproof agentproof Public

    Experimental assurance manifests and policy checks for AI agents and MCP integrations. Local CLI, synthetic fixtures and GitHub Action.

    Python