zero-skills
Warn
Audited by Snyk on Apr 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's README and SKILL.md plus the getting-started/claude-code-guide.md explicitly instruct the agent to clone and load external GitHub repositories (e.g., https://github.com/zeromicro/zero-skills and the ai-context submodule) and to reference public docs (go-zero.dev), and the Claude Code guide even supports executing shell commands to inject and load those external files as runtime context that the agent will read and act on—so untrusted, user-generated third‑party content can be fetched and can materially influence the agent's subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata