sales-deliverability

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and read platform SKILL.md files from public URLs (e.g., "WebFetch directly from this repo: https://raw.githubusercontent.com/.../skills/{skill-name}/SKILL.md") and to use those documents to ground recommendations and invocation, which means the agent will ingest and act on untrusted, public third‑party content that can materially change its actions.

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 files at runtime from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md and then use those fetched SKILL.md contents to shape prompts and invocations, so this external URL is a runtime dependency that directly controls agent instructions.