e2e

SUSPICIOUS. The skill's core behavior matches an e2e testing agent, but it grants an autonomous agent unusually broad power: install external tooling, run infrastructure, modify application code, commit changes, and write outside the repo. No clear credential-harvesting or malicious exfiltration is present, so this is not confirmed malware; the main concerns are high-impact autonomy, broad execution/write scope, and partially unverifiable install instructions hidden in referenced files.