marketing-psychology

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

• Third-party content exposure detected (high risk: 0.70). Outsider-authored free text is likely ingested at runtime because the skill is sourced from a public GitHub repository (Upstream: https://github.com/coreyhaines31/skills), and the workflow “install the upstream bundle” implies the agent will read README/asset text from that external repo into its LLM context.