autonomous-loops

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). This is a direct raw GitHub link to an install.sh (used by curl|bash patterns) which is potentially risky — even though it points to a named GitHub user/repo, executing unreviewed remote shell scripts is a common malware vector and should be verified (inspect the script, check repo authenticity and commit history) before running.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill contains an installation command that runs remote code via curl -fsSL https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh | bash, which fetches and executes external code as part of setup/usage (a required dependency for the Continuous Claude pattern), so it is a runtime external dependency that can execute code.