pp-instagram

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

• Third-party content exposure detected (medium risk: 0.30). Direct use runs the outsider-authored user query (from $ARGUMENTS) to select/execute an instagram-pp-cli command with --agent, and the CLI can ingest and emit data from Instagram/competitor discovery and comments/media outputs at runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's install instructions explicitly run remote installs that fetch and execute code (e.g., "go install github.com/mvanhorn/printing-press-library/library/social-and-messaging/instagram/cmd/instagram-pp-cli@latest"), and the CLI fetched from github.com/mvanhorn/... is a required dependency for runtime.