publish-repo

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow runs npx skills add . --list and npx skills add <owner>/<repo> --skill '*' ... which causes the agent to ingest free-form skill metadata/README/frontmatter from the target repository’s skills/ contents (outsider-authored repo files) into the LLM context via the skills tooling during discovery/verification.