uber

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and "Read https://raw.githubusercontent.com/lucaswhch/awesome-skills/main/skills/enterprise/uber/SKILL.md and apply uber skill" (see §14 Installation and references/5 Platform Support), meaning it will ingest public third‑party content from GitHub as part of its workflow which can materially influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installation instructions tell the agent to "Read https://raw.githubusercontent.com/lucaswhch/awesome-skills/main/skills/enterprise/uber/SKILL.md" (and a similar raw GitHub URL for the uber-engineer SKILL.md), which is a runtime fetch of remote content that the agent is instructed to apply as its system prompt—meaning external content would directly control prompts at runtime.