lenny-skillpack-creator

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public Refound/Lenny content (see scripts/fetch_refound_skills.py which downloads SKILL.md or page.html and scripts/extract_lenny_skill.py plus references/WORKFLOW.md which describe extracting/normalizing that HTML/SKILL.md), so untrusted third‑party pages are parsed and used to drive conversion decisions and outputs, creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The included script scripts/fetch_refound_skills.py performs runtime HTTP fetches (e.g., https://refoundai.com/skills//SKILL.md and https://refoundai.com/lenny-skills/s// or the browse page https://refoundai.com/lenny-skills/browse/) to load remote SKILL.md content that would be injected/ingested as source instructions for conversion, so fetched content can directly control agent prompts at runtime.