lemlist

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md instructs the agent to run Membrane actions and proxy arbitrary requests to the Lemlist API (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint"), which fetches user-generated/untrusted Lemlist content that the agent is expected to 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: 0.80). The skill requires installing and running the Membrane CLI (installed via npm, e.g. https://registry.npmjs.org/@membranehq/cli or https://www.npmjs.com/package/@membranehq/cli), which fetches remote code that is executed at runtime and is a required dependency for the skill to operate.