content-brief-generator

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses the Promptwatch MCP server tools (e.g., get_content_gap_recommendations, get_citations) to pull “brief inputs” and “cited sources” at runtime, which can include outsider-authored free text from Promptwatch’s underlying public/community content; that text is then ingested into the agent’s LLM context to generate the brief.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime MCP server (https://server.promptwatch.com/mcp) which the agent calls to fetch prompts, recommendations, citations and other instructions that directly control its behavior, so this is an external runtime dependency controlling agent prompts.