create

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs constructing and running a CLI that includes --token {GITHUB_TOKEN}, which requires embedding the actual GitHub token value verbatim into generated commands/outputs (exfiltration risk).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's required AGENTS.md explicitly instructs agents to fetch arbitrary URLs using "curl {URL} > .temp/{filename}" and to reference those downloaded files, which means the agent will retrieve and read untrusted public web content (AGENTS.md "URL링크 참조" section) that could influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly executes "curl {URL} > .temp/{filename}" at runtime to fetch external content into the agent's working files (URL링크 참조), which lets remote content be injected into the agent context and thus can directly control prompts or contain executable instructions.