sales-integration

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 WebFetch public SKILL.md files from raw.githubusercontent.com (and to look up non-sales-* skill repos) and requires grounding recommendations in those fetched SKILL.md contents, so the agent will ingest untrusted, public third-party text that can materially influence its next actions.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill explicitly instructs the agent to WebFetch SKILL.md from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md at runtime and to ground recommendations in that fetched content, so the external file directly controls prompts/instructions and is a required dependency.