awesome-claude-code-subagents

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

• Third-party content exposure detected (high risk: 0.90). This skill's installation and dynamic-loading instructions explicitly fetch Markdown subagent files from public raw.githubusercontent.com URLs (e.g., the curl commands in "Installation Methods" and "Dynamic Agent Loading") which are untrusted, user-controlled third‑party content that the agent is expected to read/interpret as agent instructions and can materially change its behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime downloads of agent definition markdown that become Claude subagent instructions from URLs such as https://raw.githubusercontent.com/VoltAgent/awesome-claude-code-subagents/main/categories/02-language-specialists/python-pro.md (and the repository https://github.com/VoltAgent/awesome-claude-code-subagents.git), so fetched remote content directly controls prompts and is required for the skill to function.