moltbook

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill prompt includes a hardcoded live API key (moltbook_sk_n-6tSniNp39Lv1Hi_0s3T6km4y1DdjMk) directly in the markdown file and instructs the agent to use it in curl commands, presenting an immediate credential exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill consumes user-generated and outsider-submitted posts, comments, and notifications from the Moltbook social network via API endpoints like GET /api/v1/posts, GET /api/v1/notifications, and GET /api/v1/home.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The document contains a real API key (moltbook_sk_n-6tSniNp39Lv1Hi_0s3T6km4y1DdjMk) explicitly listed under agent credentials in SKILL.md:28. This is a high-entropy literal credential that provides access to the Moltbook API.