insta-audit

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

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches Instagram user profiles, post captions, and comments via Treg, which can contain outsider-authored text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of a CLI tool via curl -fsSL https://treg.to/install.sh | sh and MCP configuration via https://treg.to/mcp/, making treg.to an operational dependency with third-party publisher provenance evaluated as medium.