bryand410/mcp-scrutiny - 4 Help Wanted Issues

Open Issues Need Help

Non-English prompt injection is invisible: French steering patterns are missing 25 days ago

good first issue detector

Static and semantic security scanner for MCP servers: unpinned packages, rug pulls, tool poisoning, shadowing and toxic flows. Trained model, SARIF output, zero dependencies, fully offline.

Python

#ai-security#devsecops#llm-security#mcp#model-context-protocol#prompt-injection#python#sarif#security#static-analysis#supply-chain-security#tool-poisoning

Add a --format markdown output for pull-request comments 26 days ago

enhancement good first issue

bryand410/mcp-scrutiny

Static and semantic security scanner for MCP servers: unpinned packages, rug pulls, tool poisoning, shadowing and toxic flows. Trained model, SARIF output, zero dependencies, fully offline.

Python

#ai-security#devsecops#llm-security#mcp#model-context-protocol#prompt-injection#python#sarif#security#static-analysis#supply-chain-security#tool-poisoning

Extend the decode-and-rescore pass beyond base64 and percent-encoding 26 days ago

enhancement good first issue

bryand410/mcp-scrutiny

Static and semantic security scanner for MCP servers: unpinned packages, rug pulls, tool poisoning, shadowing and toxic flows. Trained model, SARIF output, zero dependencies, fully offline.

Python

#ai-security#devsecops#llm-security#mcp#model-context-protocol#prompt-injection#python#sarif#security#static-analysis#supply-chain-security#tool-poisoning

Reduce the known false positive on descriptions of security controls 26 days ago

enhancement good first issue

bryand410/mcp-scrutiny

Static and semantic security scanner for MCP servers: unpinned packages, rug pulls, tool poisoning, shadowing and toxic flows. Trained model, SARIF output, zero dependencies, fully offline.

Python

#ai-security#devsecops#llm-security#mcp#model-context-protocol#prompt-injection#python#sarif#security#static-analysis#supply-chain-security#tool-poisoning