ethskills
Fail
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands for project scaffolding (
npx create-eth@latest), package management (yarn install), and tool verification. - [EXTERNAL_DOWNLOADS]: Fetches installation scripts and configuration data from well-known and reputable technology organizations, including Noir-lang and AztecProtocol.
- [REMOTE_CODE_EXECUTION]: Includes specific commands for downloading and executing setup scripts via
curl | bashto install verified Ethereum development toolchains (nargo, bbup). - [DATA_EXFILTRATION]: Implements a feedback submission system that sends data to
https://ethskills.com/api/feedback. This is governed by explicit safety instructions requiring the agent to strip PII and obtain human approval before transmission. - [PROMPT_INJECTION]: The skill relies on fetching and processing external markdown content from
ethskills.com, which represents an indirect prompt injection surface. The impact is minimized by instructional guardrails and human-in-the-loop review patterns.
Recommendations
- CRITICAL: 1 infected file(s) detected - DO NOT USE
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata