msw-packages

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

• Third-party content exposure detected (high risk: 0.70). The skill's Fetch Protocol explicitly instructs the agent to WebFetch README and other files from the public GitHub repo (raw.githubusercontent.com and api.github.com) and to summarize and act on that README content, so untrusted public content from GitHub could contain instructions that influence integration actions.

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

• Potentially malicious external URL detected (high risk: 0.90). Yes — the skill explicitly performs runtime fetches of repository content (e.g., https://raw.githubusercontent.com/MSW-Git/MSWPackages/main//README.md and calls to https://api.github.com/repos/MSW-Git/MSWPackages/git/trees/main?recursive=1) and uses those fetched files to drive the agent's summarization/integration decisions, so the external content directly controls agent behavior and is a required dependency.