code-climate

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to use Membrane actions (e.g., membrane action run / list for actions like list-snapshot-issues, get-repository-snapshot, list-test-reports) to fetch and interpret Code Climate repository/snapshot/issue/test-report data from external (user-controlled) Code Climate accounts, which are untrusted third-party content that can influence subsequent agent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running the Membrane CLI via the external package reference "npm install -g @membranehq/cli@latest", which fetches remote code that will be installed and executed at runtime and is a required dependency for the skill.