huginn-onboard
Fail
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides 'Quick Start' instructions that download remote shell scripts and pipe them directly into bash for execution. This bypasses any local script verification and allows for arbitrary code execution from external sources.
- Evidence in SKILL.md:
curl -sSL https://raw.githubusercontent.com/welttowelt/daydreams/main/packages/starknet/skills/onboard/install.sh | bash - Evidence in META-SKILL.md:
curl -sSL https://raw.githubusercontent.com/keep-starknet-strange/starknet-agentic/main/skills/huginn-onboard/meta-install.sh | bash - [EXTERNAL_DOWNLOADS]: The skill fetches executable logic from unverified GitHub repositories belonging to the author and organization accounts rather than using pinned versions in a secure package registry.
- [COMMAND_EXECUTION]: The skill executes external CLI tools and scripts with user-supplied arguments, creating a surface for command injection if inputs are not strictly validated by the target scripts.
- Evidence: Usage of
npx starknet-account deployand the piped bash execution with arguments like--agent-name.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/welttowelt/daydreams/main/packages/starknet/skills/onboard/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata