lenny-skillpack-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads and ingests public Refound/Lenny pages (see scripts/fetch_refound_skills.py which fetches SKILL.md or page.html from refoundai.com and the workflow that requires "source skill content"), so the agent will read and parse untrusted third-party web content that could contain embedded instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The included script scripts/fetch_refound_skills.py performs runtime HTTP fetches of external SKILL.md pages (e.g., https://refoundai.com/skills//SKILL.md and https://refoundai.com/lenny-skills/s//) and writes/ingests that content, which can directly control the agent’s input/prompting when parsed, so this is a runtime dependency that can inject remote instructions.