skill-installer

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 GitHub repositories and the VoltAgent/awesome-agent-skills catalog, which involves reading external skill files and repository content authored by third parties.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill describes downloading and installing remote agent skills from arbitrary GitHub repositories and catalogs via an external python script, presenting weak or unknown third-party operational dependencies.