media-relations

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect prompt injection surface identified. Ingestion points: User input enters via the intake process (references/INTAKE.md). Boundary markers: The templates in references/TEMPLATES.md do not use delimiters to isolate user data. Capability inventory: The skill only generates text and has no access to system commands or external networks. Sanitization: No sanitization of user-provided content is performed.
  • NO_CODE (LOW): The skill is entirely instruction-based and contains no executable components.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:26 AM