missive

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

• Third-party content exposure detected (high risk: 0.70). The skill’s SKILL.md shows it connects to Missive via the Membrane CLI and runs actions or proxy requests (see "Working with Missive", "Running actions", and "Proxy requests"), which involves fetching user-generated messages/conversations from Missive that the agent would read and could materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running the external Membrane CLI (e.g., via "npm install -g @membranehq/cli" and "npx @membranehq/cli@latest"), which fetches and executes remote code at runtime and is a required dependency for the skill.