qiaomu-opencli-oneshot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt contains a hardcoded public Twitter Bearer token string in an example template snippet, which violates secure credential handling guidelines.

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

• Third-party content exposure detected (low risk: 0.10). The workflow navigates to web pages via browser automation and parses page content and API responses, which involves fetching arbitrary web pages (low risk).