debate-hall-admin — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited debate-hall-admin (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.
===DEBATE_HALL_ADMIN===
META: TYPE::SKILL[FOCUSED] VERSION::"1.0" PURPOSE::"Admin operations for safety and redaction" ROUTER::debate-hall WARNING::"Use with caution - these are override operations"
§1::TOOLS
FORCE_CLOSE_DEBATE::[ PURPOSE::"I5 safety kill switch - emergency debate termination", PARAMS::[thread_id::REQUIRED,reason::REQUIRED[logged]], EFFECT::closes_any_state[ACTIVE,PAUSED] ]
TOMBSTONE_TURN::[ PURPOSE::"Redact turn content preserving hash chain (I4 compliance)", PARAMS::[thread_id::REQUIRED,turn_index::REQUIRED[0-based],reason::REQUIRED], EFFECT::content_replaced_with_tombstone[hash_preserved] ]
§2::SAFETY_NOTES FORCE_CLOSE::"Use for runaway debates, safety violations, or structural integrity threats" TOMBSTONE::"Use for PII exposure, harmful content, or audit requirements" AUDIT::"All admin actions are logged with reason"
===END===
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.