align-repo

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains a self-update execution step that downloads and installs external packages from a remote repository upon initiation, which represents untrusted remote code execution and installation behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill includes an operational self-update instruction executing npx skills add https://github.com/apocohq/skills --skill align-repo from an arbitrary third-party repository (apocohq/skills), representing an unverifiable remote external dependency with weak/unknown provenance.