nfadp

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE]: The skill documentation in 'Paso 6' references a hardcoded local file path: C:/Users/cmano/claude-seo/[cliente]/auditoria_nfadp_[fecha].md. This pattern exposes a specific local directory structure and a username ('cmano') associated with the author's development environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit external websites, creating a surface for processing untrusted content.
  • Ingestion points: External website content is fetched as the primary data source in 'Paso 1'.
  • Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to disregard potential commands embedded in the audited website's text.
  • Capability inventory: The skill requires file-writing capabilities to generate the audit report (Paso 6).
  • Sanitization: There are no explicit instructions for sanitizing or escaping the data retrieved from the target URL before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 12:02 AM
Security Audit — agent-trust-hub — nfadp