gh-aw-operations

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly uses imports (e.g., "imports:
• owner/repo/.github/agents/agent-name.agent.md@main" and examples under "Import External Agent/Skill"), which fetches and incorporates arbitrary external GitHub repository content that the agent is expected to read and act on, allowing untrusted third-party instructions to influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill uses imports that fetch external repository content at runtime which can directly inject agent instructions (e.g., thomast1906/github-copilot-skills-terraform/.github/agents/terraform-provider-upgrade.agent.md@main), so the external repo content can control prompts.