bdistill-behavioral-xray — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bdistill-behavioral-xray (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Systematically probe an AI model's behavioral patterns and generate a visual report. The AI agent probes itself — no API key or external setup needed.
bdistill's Behavioral X-Ray runs 30 carefully designed probe questions across 6 dimensions, auto-tags each response with behavioral metadata, and compiles results into a styled HTML report with radar charts and actionable insights.
Use it to understand your model before building with it, compare models for task selection, or track behavioral drift over time.
pip install bdistill
claude mcp add bdistill -- bdistill-mcp # Claude CodeFor other tools, add bdistill-mcp as an MCP server in your project config.
In Claude Code:
/xray # Full behavioral probe (30 questions)
/xray --dimensions refusal # Probe just one dimension
/xray-report # Generate report from completed probeIn any tool with MCP:
"X-ray your behavioral patterns"
"Test your refusal boundaries"
"Generate a behavioral report"| Dimension | What it measures |
|---|---|
| tool_use | When does it call tools vs. answer from knowledge? |
| refusal | Where does it draw safety boundaries? Does it over-refuse? |
| formatting | Lists vs. prose? Code blocks? Length calibration? |
| reasoning | Does it show chain-of-thought? Handle trick questions? |
| persona | Identity, tone matching, composure under hostility |
| grounding | Hallucination resistance, fabrication traps, knowledge limits |
A styled HTML report showing:
/distill --adversarial) alongside behavioral probes for complete model profiling@bdistill-knowledge-extraction - Extract structured domain knowledge from any AI model~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.