sprinklr

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to use Membrane to list/run actions and proxy requests against Sprinklr (e.g., reading Posts, Comments, Conversations, Forum Threads via the Sprinklr API), which are user-generated/untrusted social media and forum contents that the agent will read and act on.

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 "npm install -g @membranehq/cli" (which fetches and executes remote code from the npm registry as a required dependency used at runtime), so this external package fetch executes remote code and is therefore a runtime risk.