ecosystem-health
Warn
Audited by Snyk on Feb 16, 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 mandatorily fetches and parses open/public documentation and the changelog (e.g., via docs-management using raw-githubusercontent-com-anthropics-claude-code-refs-heads-main-CHANGELOG and live docs sections), and it reads/interprets that external content at runtime for categorization and audits, exposing the agent to untrusted third-party input.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill mandatorily fetches the changelog at runtime using the doc ID "raw-githubusercontent-com-anthropics-claude-code-refs-heads-main-CHANGELOG" (i.e. raw.githubusercontent.com/.../CHANGELOG), and that fetched content is used to drive parsing, categorization, and to spawn/seed the claude-code-guide agent (thereby directly controlling prompts/instructions).
Audit Metadata