github-copilot-starter

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory "MANDATORY FIRST STEP" requires using the fetch tool to retrieve and adapt content from public GitHub URLs (e.g., https://github.com/github/awesome-copilot/... and https://raw.githubusercontent.com/github/awesome-copilot/...), so the agent will ingest untrusted, user-generated third-party webpages and use their content to drive configuration and file-generation decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill explicitly requires fetching and adapting instructions at runtime from the awesome-copilot repository (e.g. https://raw.githubusercontent.com/github/awesome-copilot/main/instructions/[relevant-file].instructions.md), which would directly inject externally hosted content that controls the agent's prompts/instructions.