sales-prospect-list

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 repo (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md) and to read them before recommending a platform, which means the agent will fetch and interpret untrusted public third‑party content that can change its subsequent tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to WebFetch platform SKILL.md files at runtime from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md and to ground its recommendations/invocations on that fetched content, so remote content would directly control the agent's prompts.