find-skills-for-project

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

• Third-party content exposure detected (low risk: 0.10). The workflow researches and vets third-party community-authored agent skills from GitHub and skills.sh by reading their remote content and documentation.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute npx -y skills@latest, which dynamically fetches and runs a third-party package from npm at runtime, resulting in a weak/unknown/suspicious operational dependency.