skills/huangcheng/skills/youdao-note/Gen Agent Trust Hub

youdao-note

Fail

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The setup instructions include a command that downloads a script from https://artifact.lx.netease.com/download/youdaonote-cli/install.sh and pipes it directly into the bash interpreter. This pattern allows for arbitrary code execution on the user's system without prior inspection of the script's contents.\n- [EXTERNAL_DOWNLOADS]: The skill fetches an installation script and potentially other components from artifact.lx.netease.com, which is an external domain not included in the provided trusted list.\n- [COMMAND_EXECUTION]: The skill relies on executing the youdaonote CLI tool and other shell utilities (like jq and cat). It constructs and executes shell commands which can be a risk if inputs from external sources are not properly sanitized.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external data from notes and web pages.\n
  • Ingestion points: The skill reads note content via youdaonote read and clips web content via youdaonote clip.\n
  • Boundary markers: There are no markers or instructions used to separate the external data from the agent's instructions.\n
  • Capability inventory: The skill can execute local CLI tools, write to the file system, and interact with network services through the CLI.\n
  • Sanitization: The skill does not perform any sanitization or validation of the content retrieved from notes or web pages before processing it.
Recommendations
  • HIGH: Downloads and executes remote code from: https://artifact.lx.netease.com/download/youdaonote-cli/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 15, 2026, 02:34 PM