edit-config

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads configuration templates and catalogs from a specified GitHub repository branch, which constitutes reading outsider-authored content via repository files.

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

• Potentially malicious external URL detected (medium risk: 0.30). An operational dependency is fetched from the GitHub repository https://github.com/Mizoreww/awesome-agent-config.git to provide instructions and configuration files (INSTALL.md, catalog.md, etc.) that govern the agent's behavior during runtime, presenting a common/reputable unofficial third-party dependency.