uber-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 and Installation sections explicitly instruct the agent to "Read https://raw.githubusercontent.com/lucaswhch/awesome-skills/main/skills/enterprise/uber/uber-engineer/SKILL.md and apply uber-engineer skill", which requires fetching and ingesting a public GitHub raw URL (untrusted third-party content) that the agent is expected to apply and which could change its behavior or 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 instructs platforms to "Read https://raw.githubusercontent.com/lucaswhch/awesome-skills/main/skills/enterprise/uber/uber-engineer/SKILL.md and apply uber-engineer", meaning the raw GitHub URL is fetched at runtime to populate system prompts and thus can directly control agent instructions.