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 scripts (scripts/list-skills.py and scripts/install-skill-from-github.py, via scripts/github_utils.py) fetch and download content from arbitrary GitHub repos/URLs (public or user-provided), and the installer ingests those repo directories (including SKILL.md and code) into the agent's skills directory, exposing the agent to untrusted, user-generated third-party content.

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

• Potentially malicious external URL detected (high risk: 0.90). The installer scripts perform runtime fetches of GitHub-hosted skill content (e.g., https://codeload.github.com/{owner}/{repo}/zip/{ref} and the GitHub API URL https://api.github.com/repos/{repo}/contents/{path}?ref={ref}), downloading and installing remote SKILL.md and code into the agent's skills directory — content that can contain instructions or executable code that will control agent behavior.