Prempti - Falco-powered policy and visibility layer for AI coding agents

Prempti is an experimental tool from Falco Security that provides guardrails and real-time visibility for AI coding agents by intercepting tool calls before they execute. It evaluates every shell command, file write/edit/read, web fetch, and MCP call against customizable Falco rules written in YAML, producing verdicts: Allow (proceeds), Deny (blocked with LLM-friendly explanation), or Ask (prompts user for approval). Two operational modes are available: Guardrails mode (default, verdicts enforced) and Monitor mode (observe-only, all calls proceed while verdicts are logged). A default ruleset covers working-directory boundaries, sensitive paths (.env, ~/.ssh/, cloud credentials), sandbox disable attempts, credential access, destructive commands, exfiltration, MCP server config poisoning, skill file injection, and persistence vectors. Users can add custom rules to ~/.prempti/rules/user/. A Claude Code skill is included for interactive rule authoring. Supported agents include Claude Code (Linux, macOS, Windows, on x86_64 and aarch64) and experimental support for Codex. Installation is via .pkg (macOS), tar.gz with install script (Linux), or .msi (Windows). The tool is written primarily in Rust (83.4%), has 109 stars and 14 forks, and is licensed under Apache 2.0. The documentation notes it is not a sandbox or OS-level security, but a cooperative policy layer that works alongside containment techniques. The project was built with assistance from Claude Code. 

https://github.com/falcosecurity/prempti

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
Read more

Secure Vibe Coding Guide: Best Practices for Writing Secure Code

Ken Huang's "Secure Vibe Coding Guide" emphasizes the importance of integrating security into the software development lifecycle. The guide provides best practices for writing secure code, including input validation, proper authentication mechanisms, and secure data storage techniques. It also highlights the necessity of regular code reviews and staying updated with the latest security vulnerabilities and patches. By following these guidelines, developers can create applications that are resilient against common security threats and contribute to a safer digital environment.  https://kenhuangus.substack.com/p/secure-vibe-coding-guide
Read more