directory-submissions

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified. The skill is entirely focused on content strategy and educational guidance.\n- [PROMPT_INJECTION]: The skill provides instructions for the agent to use a specific persona and avoid conversational filler such as disclaimers or warnings. These are stylistic constraints for high-quality text generation and do not attempt to override safety filters.\n- [PROMPT_INJECTION]: The skill ingests user-provided text for product listings, creating a surface for indirect prompt injection. This is assessed as safe because the skill lacks the capabilities to perform dangerous actions or access system resources.\n
  • Ingestion points: User-supplied product data used for generating directory listings.\n
  • Boundary markers: None identified in the provided text.\n
  • Capability inventory: Restricted to text generation; no shell or tool access.\n
  • Sanitization: Not required for the identified use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:12 AM
Security Audit — agent-trust-hub — directory-submissions