sales-brand24

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

• Third-party content exposure detected (high risk: 0.85). Brand24 monitoring mentions are sourced from public web/social/news/forums and the skill’s runtime flow reads those mention texts (outsider-authored) via Brand24’s platform reference/MCP/API to answer the user’s question.

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 fetch remote skill descriptions from raw GitHub URLs (e.g., https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md), and that fetched SKILL.md content is used to ground/rule the agent's routing and prompt generation, so this is a runtime external dependency that directly controls agent instructions.