sales-side-project-valuation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch platform SKILL.md files from the public URL https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md and to read those external platform SKILL.md files before recommending or routing, which requires ingesting untrusted public third‑party content that can influence tool use and decisions.

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 and read SKILL.md files from raw GitHub URLs (https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md), which means external content fetched from that URL will directly control prompts/invocations and is treated as a required dependency for routing/recommendations.