super-pm-upgrade

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches from the remote Git repository (see "git fetch --tags" in Step 2) and then reads/display commit messages via "git log --pretty=format:"- %s" $CURRENT_VERSION..$LATEST_TAG" in Step 4, meaning it ingests untrusted, user-generated repository content (commit messages/tags) as part of the workflow and uses that content to decide whether to upgrade—creating a clear vector for indirect prompt injection.