skill-installer
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill fetches and installs skills from arbitrary GitHub repositories (including public repos and user-provided repo/paths) and reads the curated list via the GitHub API, so it ingests untrusted, user-generated third-party content from the open web (GitHub) as part of its workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill-installer fetches and installs skill code at runtime from GitHub (e.g. https://github.com/openai/skills/tree/main/skills/.curated and arbitrary repos via https://github.com///tree//), which can deliver remote code or prompt-instructions that the agent will install/execute.
Audit Metadata