soci

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

• Third-party content exposure detected (high risk: 0.80). The skill’s SKILL.md instructs the agent to connect to Soci via the Membrane CLI and run actions (see "Connecting to Soci" and "Running actions"), which will retrieve Soci/social‑network content (user-generated, public social media data) that the agent is expected to read and that could materially influence subsequent decisions or tool use.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires and invokes the Membrane CLI at runtime (e.g., "npx @membranehq/cli@latest" / "npm install -g @membranehq/cli@latest"), which will fetch and execute remote code from the npm registry and is a required dependency for the skill.