vmware-engineer

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

• Third-party content exposure detected (high risk: 1.00). The skill's Platform Support (§10) explicitly instructs agents to "Read [URL] and install" from a raw GitHub URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/vmware/vmware-engineer/SKILL.md), which is a public, user-controlled source that the agent would ingest and could alter its behavior, meeting the conditions for indirect prompt injection risk.

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

• Potentially malicious external URL detected (high risk: 1.00). The Platform Support instructs runtime "Read [URL] and install" pointing to https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/vmware/vmware-engineer/SKILL.md, which would be fetched at runtime and whose content (the system prompt/skill instructions) directly controls agent behavior and is treated as a required install dependency.