RankClaw – AI-audited all 14,706 OpenClaw skills; 1,103 are malicious
Found 1,103 malicious skills (7.5%) that pattern matching missed; AI audit detects prompt injection in docs.
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, and Hermes.
Two-pass detection with 109-entry word replacement table across three tiers.
Content creators and developers using AI writing assistants
GPTZero · Originality.ai · HuggingFace detect-gpt
Found 1,103 malicious skills (7.5%) that pattern matching missed; AI audit detects prompt injection in docs.
Self-modifying skills let agents persist new behaviors without restarts or config edits.
Yet another AI content wrapper claiming human-sounding output in a saturated market.
Real-time cost tracking for Claude Code sessions; saves money intuition before you ship.
60+ threat patterns in sub-2s, but OpenClaw's ecosystem appears niche and unverified.
DuckDB+dbt+Snowflake skills for OpenClaw agents, but early and depends entirely on OpenClaw adoption.