tools-marketplace-inventory

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs local marketplace scanning scripts that read markdown/YAML frontmatter from marketplace/bundles/ (outsider-authored repository content) and then serialize that extracted text into TOON/JSON printed to stdout and/or written to .plan/temp/..., which can be ingested into the agent’s LLM context.