install-skills

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

• Third-party content exposure detected (low risk: 0.10). The workflow installs agent skills from external sources (such as GitHub repositories) specified by the user, which involves fetching third-party content that the agent then ingests.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill uses npx --yes skills@latest to install agent skills from an unspecified external source, which constitutes an unverifiable runtime external dependency from the npm registry.