sync-local-global-agents-skills

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external skills from GitHub via fetchFromGitHub and downloads skill files into the local agent directory, exposing the agent to untrusted file content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an operational dependency fetching content from the GitHub repository https://api.github.com/repos/AVIDS2/memorix/contents/plugins/... during runtime execution, which constitutes an unofficial external dependency with weak/unknown provenance.