gsd-orchestration

Warn

Audited by Snyk on Feb 28, 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 explicitly spawns a "Researcher" subagent and lists WebSearch/WebFetch in allowed tools (references/ARCHITECT-INTEGRATION.md, references/COMMANDS-REFERENCE.md, SKILL.md), which causes the agent to fetch and ingest open web content (RESEARCH.md) that is then loaded into planning/architecture files and can directly influence planning, tool selection, and execution decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 07:52 AM