marketing-schema

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to ingest content from external files like .agents/product-marketing.md without safety boundaries.
  • Ingestion points: SKILL.md instructs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before performing tasks.
  • Capability inventory: The agent generates functional JSON-LD markup and provides marketing implementation guidance.
  • Boundary markers: The instructions do not specify delimiters or provide warnings to ignore embedded instructions within these external context files.
  • Sanitization: There is no requirement for validation or sanitization of the data retrieved from external context files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:46 PM
Security Audit — agent-trust-hub — marketing-schema