sales-cadence

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to WebFetch and read platform SKILL.md files from public GitHub raw URLs (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md) and to look up other repos via references/skill-sources.md, meaning it ingests open/public third‑party content that the agent must interpret to decide recommendations and tool use.

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 at runtime to WebFetch platform SKILL.md files from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md (example: https://raw.githubusercontent.com/sales-skills/sales/main/skills/sales-mailshake/SKILL.md), and those fetched documents are required and used to directly ground and control the agent's recommendations/prompts.