snap-scope

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read GitHub issues and referenced parent PRDs/epics via gh issue view, which are user-generated third-party pages the agent will interpret and use to drive decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching GitHub issue/PRD content at runtime (e.g., https://github.com///issues/ via gh issue view), which injects remote text directly into the agent's context and can therefore control prompts.