Evaluates user-generated content moderation, spam prevention, report/block systems, content policies, and abuse detection mechanisms.
21
Total Checks
3
Delivery Formats
3
Categories
7
Versions
Quality hardening: added numeric thresholds to all checks, cross-references between related checks, anti-sycophancy patterns (enumeration, quoting, negative guardrails, measurement-on-pass), expanded pass criteria and remediation code blocks
2026-04-02
Added chunked format for browser-based tools
2026-03-01
Improved Step 3: paste URL is now primary submission method
2026-03-01
Hardened curl commands with -sS -L flags for redirect following and error visibility. Added response validation guidance to Step 3.
2026-02-23
Fixed invalid prompt_hash — replaced placeholder/non-hex value with actual SHA-256 digest of prompt content
2026-02-23
Removed deprecated category, duplicate check, and orphan template entry (22 to 21 checks); rebalanced 5 severities
2026-02-21
Initial release
2026-02-21