injection-detector
io.github.viridis-security/injection-detector
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
This endpoint completed initialize and tools/list. No tool was called.
- Rank
- #1846
- Score
- 82
- Tool tokens
- 723
- Tools
- 2
Tools
Token cost is the o200k count of the tools list JSON, including schemas, before any tool is called.
detect_injection
Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adve
detect_trace_tool_policy
Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call e
Nearby in GitHub
Up-to-date code docs for any prompt
MCP server for Financial Modeling Prep API with 250+ financial data tools
Official SerpApi MCP server for Google, Bing, and other search engines.
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools