GraphCanon updated Oct 18, 2026 · GitHub synced Oct 18, 2026
Decision brief
Unverified catalog guidance: kereva-scanner is a specialized code scanner that assesses AI prompts and interactions with language models for potential security vulnerabilities and performance inefficiencies.
Good fit when
- Unverified catalog guidance: When you are developing applications involving AI-generated content or integrations with large language models, to ensure your prompts are secure against attacks such as prompt injection.
- Unverified catalog guidance: If you need to comply with OWASP LLM Top 10 guidelines, because kereva-scanner specifically addresses these security standards for AI code.
Avoid when
- Unverified catalog guidance: When your project does not involve interactions with language models or AI-generated content, since the scanner's utility is primarily in evaluating AI-related issues.
- Unverified catalog guidance: If you are looking for a comprehensive general code linter that checks for coding standard violations or general best practices unrelated to security and performance of LLMs.
- Pricing:
- freemium - The tool is free under the Apache-2.0 license but may have features in a paid version not detailed in the repository.
- Requirements:
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (559d since push)
- As of Oct 18, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 18, 2026
- Security (OSV)
- 2 low
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
Package installation is not established from the available documentation. Check the source repository for setup instructions.
git clone https://github.com/kereva-dev/kereva-scannerSource repositorySimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A code-scanning tool that evaluates AI prompts and LLM interactions for security and performance issues.
Capability facts
- MCP server
- Unknown; MCP server not established by this scan
Source: repo_scan · Oct 18, 2026
- Languages
- python
Source: github.language · Oct 18, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (readme_declaration_v2, Oct 18, 2026)
pip install -r requirements.txtSource link
Tags
README
Install dependencies pip install r requirements.txt ``` 📄 License This project is licensed under the Apache License 2.0 see the LICENSE file for details.
For agents
This page has a .md twin and JSON over the API.