ugc-brief-generator

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues or malicious patterns were identified in the skill files. The logic is restricted to generating text-based content briefs based on user input.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests user-provided data to generate content.
  • Ingestion points: User input for product details and campaign objectives in SKILL.md.
  • Boundary markers: Absent; user input is interpolated into the brief template without delimiters.
  • Capability inventory: The skill lists Read and Write tools but does not use them to process or execute user-provided data.
  • Sanitization: No validation or filtering is performed on external inputs.
  • This surface is typical for content generation skills and poses no significant risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:26 AM
Security Audit — agent-trust-hub — ugc-brief-generator