secchecker is an open-source static security scanner designed for AI agents, MCP tools, and LLM applications. It identifies vulnerabilities such as prompt injection, tool poisoning, and agentic weaknesses, tagging issues according to the OWASP LLM Top 10. The tool is aimed at AI developers and security engineers seeking to secure generative AI systems.
In the LLM eval & observability space, secchecker takes a focused approach. It focuses on detecting security vulnerabilities such as prompt injection and tool poisoning in AI agent and LLM application code. secchecker is an open-source project aimed at AI developers and security engineers. secchecker is open source under the MIT license. It ships for the command line.
It is developed by vishnu-77, and it first shipped in 2025. Development happens publicly on GitHub with 11 commits in the last 90 days. Among its 5 catalogued features are static analysis, prompt injection detection, and tool poisoning detection.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do