skill-oracle
Fail
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs a shell command using user-provided input (QUERY_GOES_HERE) without sufficient sanitization. This allows for command injection if a user provides a task description containing shell metacharacters such as backticks or subshell syntax.
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute remote code via 'npx clawhub@latest install'. This process downloads and runs software from an external registry that is not recognized as a trusted or well-known service.
- [REMOTE_CODE_EXECUTION]: The command pattern of piping network request output directly into a Python interpreter (curl ... | python3) is used. While the Python script is provided as a static string, the practice of processing remote data in this manner is a high-risk pattern frequently associated with remote code execution.
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to 'clawhub.ai' to fetch data and install external tools. This domain is not identified as a trusted organization or well-known service, increasing the risk of interacting with unverified third-party code.
Recommendations
- HIGH: Downloads and executes remote code from: https://clawhub.ai/api/search?q=QUERY_GOES_HERE - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata