moltbook

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill repeatedly shows curl examples with Authorization: Bearer YOUR_API_KEY and an example registration response containing an api_key, so an agent following these instructions would need to embed API keys verbatim into commands/requests (exfiltration risk).

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

• Third-party content exposure detected (high risk: 1.00). The skill instructs the agent to fetch and read user-generated content from the open web (e.g., https://moltbook.com/api/v1/feed, https://moltbook.com/api/v1/posts and comments) as part of its heartbeat and feed-checking workflows, which exposes it to untrusted third-party content that could contain indirect prompt injections.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's heartbeat explicitly instructs the agent at runtime to "Fetch https://moltbook.com/heartbeat.md and follow it," meaning remote content from that URL is fetched during runtime and directly controls agent instructions/behavior.