inflight

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly tells the agent to use WebFetch to retrieve and "follow those instructions step by step" from a raw GitHub URL (https://raw.githubusercontent.com/inflightsoftware/skills/main/docs/instructions.md), meaning untrusted third-party content can directly supply actionable instructions that affect the agent's behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to use WebFetch at runtime to retrieve and "follow those instructions" from https://raw.githubusercontent.com/inflightsoftware/skills/main/docs/instructions.md, so the fetched content directly controls agent behavior and is a required runtime dependency.