autonomous-loops
Fail
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the user to install a tool called 'continuous-claude' using the command 'curl -fsSL https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh | bash'. This executes an unvetted remote script directly in the user's shell.
- [EXTERNAL_DOWNLOADS]: The skill references and promotes the download of code from a third-party GitHub repository ('AnandChowdhary/continuous-claude') that is not associated with the skill author or any trusted vendor.
- [COMMAND_EXECUTION]: Multiple examples demonstrate the use of shell scripts to automate agent tasks, involving direct command execution like 'npm run build', 'npm test', and 'gh run list'.
- [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by ingesting untrusted data (specification files and CI logs via 'gh run view') directly into agent prompts without boundary markers or sanitization. This allows an attacker who can modify these external sources to influence agent behavior. The agent has significant capabilities including file system access and shell command execution.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata