gm

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external URLs and repository content via fetch, browser, cdp, and GitHub API/git history, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script URLs retrieved from GitHub raw endpoints (raw.githubusercontent.com) are common/reputable unofficial locators (individual-owned repository AnEntrypoint/gm) that fetch executable installation code during runtime setup, constituting an operational external dependency.