autoresearch

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.85). The skill exposes powerful autonomous capabilities—running arbitrary shell/HTTP commands, committing/reverting code, deploying, cloning/executing external code in CI, and using user credentials (gh api)—which, despite many stated safeguards, create strong avenues for data exfiltration, remote code introduction, and supply-chain or backdoor abuse if misused or if safeguards are bypassed.