intel-engineer

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

• Third-party content exposure detected (high risk: 1.00). The skill's §10 "Platform Support" explicitly instructs agents to "Read [URL] and install" from a public GitHub raw URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/intel/intel-engineer/SKILL.md), meaning the agent would fetch and act on open/public third-party content that could change its behavior and enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The Platform Support section instructs runtime fetching ("Read [URL] and install") of the skill file at https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/intel/intel-engineer/SKILL.md, and that fetched SKILL.md contains the system prompt and instructions that would directly control the agent at runtime, making it a required external dependency.