sales-enrich

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 platform SKILL.md files from public GitHub URLs (e.g., "WebFetch ... https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md"), which requires ingesting open, third‑party content and grounding recommendations on that content—allowing external page content to materially influence tool selection and next actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to WebFetch platform SKILL.md files from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md and then "ground your recommendation" on that fetched content, meaning remote text is fetched during execution and directly controls the agent's prompts/instructions.