manage-slash-commands

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

• Third-party content exposure detected (high risk: 0.90). The skill's dynamic_context and examples in SKILL.md explicitly run bash commands whose output is included in the expanded prompt (e.g., "Context from git:
• Changes: ! gh pr diff $1
• Status: ! gh pr view $1 --json state" and the "The bash commands execute and their output is included in the expanded prompt" note), which clearly ingests user-generated third‑party content (GitHub PRs/remote data) that the agent will read and can influence subsequent decisions and tool use.