awn
Fail
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the user to install a CLI tool by piping a remote script directly into bash:
curl -fsSL https://raw.githubusercontent.com/ReScienceLab/agent-world-network/main/packages/awn-cli/install.sh | bash. This allows for arbitrary code execution from a source outside the control of the skill platform. - [EXTERNAL_DOWNLOADS]: The skill fetches and executes content from an external GitHub repository (
ReScienceLab/agent-world-network) which is not a verified or well-known trusted vendor. - [COMMAND_EXECUTION]: The skill operates by executing local shell commands (
awn daemon start,awn send, etc.) and manages system-level resources such as PIDs and IPC ports. - [DATA_EXPOSURE]: The skill manages sensitive cryptographic identity files (
~/.awn/identity.json) which contain Ed25519 keypairs. While not direct exfiltration, the skill's architecture involves sending signed messages and peer discovery through an external gateway (https://gateway.agentworlds.ai).
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/ReScienceLab/agent-world-network/main/packages/awn-cli/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata