Capability drift in FantasyLab-ai/aurora
Aurora MCP server — glass-box statistical analysis for AI agents: 19 research-grade methods, cited findings, integrity-hashed bundles, zero invented numbers. Now with a calibration engine: measured false-fire rates attached to changepoint findings, verdicts downgraded when the data can't support the claim. Local-first.
- maintainer
- FantasyLab-ai
- tools
- 0
- CVEs
- 0
- releases
- 4
HIGH FantasyLab-ai/aurora
code analysis flagged dynamic code execution in FantasyLab-ai/aurora
current permission surface (inferred):
- HIGH code analysis flagged dynamic code execution in FantasyLab-ai/aurora you are here
Each entry is one capability capture differing from the one before it — a review signal, not a verdict.