neta-character

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports global searching and using PUBLIC character Tokens (see "Query Existing Characters" / "search_character_or_elementum" and the accessibility: PUBLIC field in SKILL.md and references), meaning the agent will fetch and consume user-generated public character descriptions which the docs state "directly affects how Agents understand the character" and thus can influence subsequent prompt/tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's examples instruct running npx -y @talesofai/neta-skills@latest which fetches and executes a remote npm package at runtime (from the npm registry) — a required runtime dependency that runs external code.