sales-coaching

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 (under "Before recommending a specific platform skill") to WebFetch public SKILL.md files from raw.githubusercontent.com and to read those files before invoking or recommending platform skills, which requires fetching and interpreting open, user-maintained third‑party content that can materially influence the agent's recommendations and tool-use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to WebFetch platform SKILL.md files from https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md and to read them before recommending or invoking platform skills, meaning remotely fetched markdown directly controls agent prompts/invocations.