autoresearch-agent

SUSPICIOUS: the skill’s core behavior matches its stated purpose, but its footprint is high-risk by design because it enables indefinite autonomous file modification, git state changes, and execution of arbitrary evaluation commands. Install trust is mixed: same-author GitHub sourcing is coherent, yet distribution is mutable/manual and the ClawHub package reference was not fully verified. No strong evidence of credential theft, exfiltration, or hidden behavior was found.