neta-elementum

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly supports global searching and use of public Elementa (search_character_or_elementum and PUBLIC accessibility in SKILL.md/references/elementum-field-guide.md) and stores agent-facing "description" and "prompt" fields that agents are expected to read and use (e.g., passed directly to make_image or guiding agent composition), so untrusted user-generated element content could materially influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill repeatedly instructs running a remote npm CLI via npx (npx -y @talesofai/neta-skills@latest), which fetches and executes remote code at runtime and is required for login/create_elementum flows, so it is a runtime external dependency that executes remote code.