find-skills-combo

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to run "npx skills find" and to read candidate descriptions from the public skills directory (e.g., https://skills.sh and individual SKILL.md files), which ingests untrusted, user-contributed third‑party content and uses it to decide which skills to install and what actions to take.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running runtime install/search commands (e.g., "npx skills add owner/repo@skill-a" and "npx skills find" / browsing https://skills.sh/) which fetch and install remote skill packages that execute code and extend/control agent behavior, so this is a runtime external dependency that can execute remote code.