$ loading_
Audit hallucinations and grounding issues in RAG pipelines.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "hallumark" yet — see the docs or source repo.
Use hallumark to check whether this RAG system has hallucination or grounding issues, and output a prioritized issue list suitable for CI gating.
Return prioritized findings so risky changes can be blocked.
Use hallumark to scan this RAG output and return all grounding issues with severity in JSON format.
Output structured JSON for programmatic parsing and downstream handling.
Use hallumark to inspect hallucination risk in agent responses and export SARIF results for a code quality platform.
Generate a SARIF report ready for quality tooling.
Audit MCP server vulnerabilities with a local LLM and attack-pattern retrieval.
Run deterministic funnel, accessibility, and LLM visibility audits with honest reports.
Audit MCP configs for exposed access, secrets, models, and compliance AI-BOMs.
Retrieve and verify audit regulations, clauses, and audit item references.
Audit LLM-as-judge results for drift, bias, and human agreement.
Review code for security, quality, and performance issues with actionable suggestions.