sales-crm-selection

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

• Third-party content exposure detected (high risk: 0.90). The skill's "How to read it" instructions explicitly tell the agent to fetch other skills' SKILL.md files from public GitHub (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md), meaning the agent will ingest and act on arbitrary public repo content that could contain untrusted, user-authored instructions which could influence subsequent tool use and decisions.

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 files at runtime from raw GitHub URLs (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md), which means remote content is fetched during execution and used to directly shape prompts/instructions.