deco-full-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs running and ingesting remote, public code/docs (for example "deno run -A https://deco.cx/validate" and CDN app imports like "https://cdn.jsdelivr.net/gh/deco-cx/apps@...") and to search Deco docs (SearchDecoCx), so it fetches and relies on open third‑party content that can influence analysis and next actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs operators to run remote code via "deno run -A https://deco.cx/validate" (and similar deno URL invocations), which fetches and executes code at runtime and is described as a required step for block validation/report generation (e.g., validation-report.json / BLOCKS_DIAGNOSTICS.md), so https://deco.cx/validate is a runtime external dependency that executes remote code.