aiagent-material-sync

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

• Third-party content exposure detected (high risk: 0.70). The skill's Workflow (steps 3–5) explicitly runs git remote/fetch/merge (e.g., "git fetch upstream" and "git merge upstream/main"), which pulls content from external git remotes (potentially public/user-generated repositories) that the agent will ingest and use to decide merges/conflict recovery and subsequent sync actions, exposing it to untrusted third-party content.