sales-data-hygiene

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to WebFetch platform SKILL.md files from the public GitHub raw URL (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md), meaning the agent will fetch and interpret untrusted, user-editable third‑party content and use it to determine subsequent tool use and recommendations.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch SKILL.md from raw.githubusercontent.com at runtime (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/sales-mailshake/SKILL.md), and that fetched markdown is read and used to directly ground and control the agent's prompts/recommendations, making it a required remote dependency.