addsearch

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: 0.90). The SKILL.md shows the agent can run AddSearch queries and proxy arbitrary requests via Membrane to the AddSearch API (see "Searching for actions", "Running actions", and "Proxy requests"), which returns search results/web content from public sites that the agent will read and could drive subsequent actions, exposing it to untrusted third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:56 AM