joyco-logs

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches a public web index (curl -s https://hub.joyco.studio/logs.md and potentially https://hub.joyco.studio/logs/NN-slug.md) at runtime, so the LLM ingests outsider-authored free text from public web content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches runtime content from https://hub.joyco.studio/logs.md (with fallback to https://hub.joyco.studio/logs) and per-article URLs like https://hub.joyco.studio/logs/NN-slug.md and explicitly uses that fetched markdown to inform and control the agent's approach, so these URLs are runtime external dependencies that directly influence prompts.