skill-installer

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

• Third-party content exposure detected (high risk: 0.90). This skill's installer and listing scripts (scripts/install-skill-from-github.py and scripts/list-curated-skills.py, via github_utils.py) fetch content from public GitHub (codeload.github.com and api.github.com / openai/skills/.curated) and can download/install arbitrary user-provided repo paths, meaning untrusted, user-generated content (including SKILL.md and code) can be ingested and materially change agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The installer scripts fetch skill content at runtime from GitHub (e.g., https://api.github.com/repos/{repo}/contents/{path}?ref={ref} and https://codeload.github.com/{owner}/{repo}/zip/{ref}), and the fetched skill directories (including SKILL.md) directly define agent prompts/instructions and are required for installation.