alphasense

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

• Third-party content exposure detected (high risk: 0.80). This skill connects to AlphaSense via the Membrane CLI and explicitly searches and retrieves third-party public/private content (e.g., company filings, news, expert calls) as part of its required workflow in SKILL.md, meaning the agent will ingest and act on untrusted external content that could include injected instructions.

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 remote Membrane CLI (e.g., "npm install -g @membranehq/cli@latest" and "npx @membranehq/cli@latest"), which fetches and executes code from the npm registry at runtime and is a required dependency for the skill.