jfb-action-item-decorator

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a pattern for UI decorators that interact with action settings, establishing a data ingestion and modification surface.
  • Ingestion points: Data is accessed via the useLoopedAction hook as described in SKILL.md.
  • Boundary markers: The provided implementation examples do not use delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill utilizes the updateActionObj function in SKILL.md to perform writes to the WordPress database.
  • Sanitization: The tutorial code lacks explicit sanitization or validation of data before it is persisted to the action settings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:06 PM
Security Audit — agent-trust-hub — jfb-action-item-decorator