nxtg-ai/Faultline AI Trust & Safety Scanner

Forensic AI output verification — detects hallucination, manipulation, and policy violations in generated content

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
inputFile to scan (path relative to repo root, e.g. "docs/ai-output.md")noREADME.md
fail-onMinimum severity to fail the build: critical, high, medium, lownohigh
providerAI provider: gemini, openai, claude, perplexity, mock. Defaults to auto-detect from env vars.no""
output-pathPath to write SARIF outputnofaultline.sarif
namedescription
sarif-filePath to generated SARIF file
verdict-countTotal number of verdicts returned
highest-severityHighest severity found: high, medium, low, none