sparc-methodology

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 explicitly describes a "researcher" mode that performs "parallel WebSearch/WebFetch" and options like sources/citations (e.g., "researcher: Deep research with parallel WebSearch/WebFetch" and example usages requesting academic/industry/news sources), which shows the agent fetches and ingests open public web content that it reads and uses to drive decisions and workflows.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill's runtime activation method includes explicit NPX commands (e.g., "npx claude-flow" / "npx claude-flow@alpha") which will fetch and execute remote package code from https://www.npmjs.com/package/claude-flow, so this URL represents a runtime external dependency that can execute remote code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 07:38 PM