skill-manager

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

• Third-party content exposure detected (low risk: 0.10). The skill-manager installs skills from user-provided GitHub links or repositories, downloading and executing scripts (skills.sh) and reading remote skill content at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill downloads and executes code from a GitHub repository via curl in SKILL.md and scripts/skills.sh, representing an official or common repository dependency depending on provenance, but the primary dependency is on Melvynx/ai-maxxing-skills which is a common/reputable unofficial publisher (or first-party project repo), categorizing it as medium.