create-technical-spike

Warn

Audited by Snyk on Feb 25, 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.md explicitly requires using search/fetch tools to "Search existing documentation" and "Research external resources" and lists tools like search/searchResults and fetch/githubRepo (Research Strategy Phase 1 and Tools Usage), meaning the agent will ingest public third-party content (documentation, community discussions, tutorials) that it must read and use to drive decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 05:25 AM