alphasense
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
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 fetch and read AlphaSense content via Membrane commands (e.g., "membrane action run ... ACTION_ID" and "membrane request CONNECTION_ID /path/to/endpoint"), and AlphaSense serves third‑party public content (news, filings, expert calls) that the agent would ingest and could materially influence subsequent actions.
Audit Metadata