zephex

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes zephex:inspect_url (references/tools.md and SKILL.md) which fetches and cleans content from arbitrary public URLs and is documented as a tool the agent should call to read external docs, meaning untrusted third-party content can be ingested and influence subsequent decisions and tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires contacting the MCP endpoint https://zephex.dev/mcp at runtime (and the provided stdio configs use "npx -y zephex", which fetches and executes a remote npm package), so external content is fetched during runtime and can directly control agent behavior or execute code.