search-first

Warn

Audited by Snyk on Mar 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's workflow ("PARALLEL SEARCH") explicitly requires searching and evaluating third-party sources such as package registries and "GitHub / web search", meaning the agent would fetch and interpret untrusted, user-generated web content to decide adopt/extend/build actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 07:20 AM
Issues
1