vibe-prospecting

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and reference docs (SKILL.md and references/enrich.md / references/fetch.md) explicitly call fetch-entities, fetch-businesses-events and enrichments like "linkedin-posts" and "website-changes" — i.e., ingesting public websites and social media content — and those results are used to drive chaining, enrichment, and export decisions, so untrusted third‑party content can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running the remote npm package via "npx @vibeprospecting/vpai@latest" (which fetches and executes code at runtime) and references the production MCP endpoint https://vp-plugin.explorium.ai/mcp that the CLI uses to drive schemas and tool behavior, so external content is executed at runtime and directly controls the agent's prompts/operations.