sales-chatbot

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires fetching and reading SKILL.md files from public GitHub URLs (e.g., https://raw.githubusercontent.com/.../skills/{skill-name}/SKILL.md) and local ~/.claude/skills/{skill-name}/SKILL.md as part of its mandatory workflow, which pulls untrusted, user-editable third‑party content that the agent must interpret to decide actions and recommendations, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent at runtime to WebFetch SKILL.md files from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md so external content from that URL is loaded into the agent's context and can directly control prompts/instructions.