kotlin-tooling-cocoapods-spm-migration

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly directs adding swiftPackage(...) entries that reference public GitHub URLs (Phase 3.2) and tells the operator to consult GitHub releases and Swift Package Index (Researching Other Pods), meaning the workflow causes the agent/tooling to fetch and interpret public third‑party package manifests and repository content which can materially change migration actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The prompt instructs the agent to modify project files and explicitly disable Xcode's User Script Sandboxing (ENABLE_USER_SCRIPT_SANDBOXING = NO), and to run destructive cleanup (pod deintegrate, rm -rf), which constitutes bypassing a security mechanism and changing machine/project state.