pp-github-contents

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

• Third-party content exposure detected (high risk: 0.70). The required workflow uses the “--agent” mode of github-contents-pp-cli to read live repository paths (e.g., contents/fetch/plan output) from user-specified GitHub repos, so any fetched file text from an outsider-authored repo can be returned as JSON to the agent’s LLM context (indirect prompt-injection risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the runtime to run go install on remote module paths (go install github.com/mvanhorn/printing-press-library/library/developer-tools/github-contents/cmd/github-contents-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/developer-tools/github-contents/cmd/github-contents-pp-mcp@latest), which fetches and builds remote code at runtime and is a required dependency for the skill.