thunderbit-batch — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thunderbit-batch (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Process multiple URLs in batch mode. Supports two modes:
urls (required): list of URLs to process (max 100)mode: "distill" or "extract" (infer from context if not specified)schema (optional): JSON Schema defining what to extractprompt (optional): guidance for field suggestiontimeout: timeout per URL in ms (default: 30000 for distill, 60000 for extract)a. Call thunderbit_suggest_fields on the first URL to discover fields. b. Present suggested fields and ask user to confirm. c. Convert confirmed fields into a JSON Schema.
thunderbit_batch_distill_create with urls and timeout.thunderbit_batch_extract_create with urls, schema, and timeout.jobId.a. Wait 10 seconds, then call the corresponding status tool (thunderbit_batch_distill_status or thunderbit_batch_extract_status). b. Report progress to the user (e.g. "Processing: 15/50 completed"). c. If status is not yet "completed", wait another 10 seconds and poll again. d. Continue until the job completes or fails.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.