clawild-moltbook

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly shows using apify.actor("apify/twitter-scraper") to fetch and analyze tweets (public, user-generated content) and then act on that analysis (posting signals to Moltbook/Slack), so untrusted third‑party content is ingested and can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs npx to fetch and execute remote packages at runtime (npx -y @apify/mcp-server and npx -y @modelcontextprotocol/server-slack, e.g. https://registry.npmjs.org/@apify/mcp-server and https://registry.npmjs.org/@modelcontextprotocol%2Fserver-slack), which downloads and executes external code as required dependencies and therefore poses runtime risk.