sales-brandwatch

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow and examples (references/brandwatch-api-reference.md and references/platform-guide.md invoked from SKILL.md) instruct using the Brandwatch APIs to retrieve "mentions" from public social media, blogs, forums and other user-generated sources (e.g., GET /projects/{projectId}/data/mentions and the platform guide's "100M+ sources" list), so the agent is expected to ingest and act on untrusted third‑party content that could contain instructive text.