skill-architect

Warn

Audited by Snyk on Mar 5, 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 references (see references/subagent-template.md and references/self-contained-tools.md "Research Workflow" and subagent examples) explicitly require WebSearch/WebFetch and instruct the agent to read, extract, and act on content from public web pages and other third-party sources, so untrusted web content could influence decisions and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 08:57 PM