sales-account-map

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 5 "How to read it" explicitly instructs the agent to fetch and read remote SKILL.md files from public GitHub (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md) and other third‑party repos, and to ground invocation decisions on that content, which means untrusted third‑party content is ingested and can materially influence tool selection and 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 the agent at runtime to WebFetch SKILL.md files from raw GitHub (e.g. https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md) and to read that fetched content to shape recommendations/prompts, which is a remote resource controlling agent behavior.