bopomofo-rescue

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill monitors user-submitted prompts via a UserPromptSubmit hook and processes them with a local decoder script, meaning outsider-authored free text in user messages is automatically ingested and parsed into the runtime workflow.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs users to clone an upstream repository (https://github.com/Oliviaiii/bopomofo-rescue.git) which acts as an operational dependency providing the required decoder script and dictionary.