marketing-ideas

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions direct the agent to read external files for product marketing context (e.g., .agents/product-marketing.md or .claude/product-marketing.md). This creates a surface for indirect prompt injection if these files are populated with untrusted content.
  • Ingestion points: SKILL.md (instructions to read context files).
  • Boundary markers: None identified; instructions do not explicitly warn the agent to ignore instructions embedded within the marketing context files.
  • Capability inventory: The skill is designed for an agent to generate marketing strategies and provide implementation steps. The surrounding agent likely has message generation and file reading capabilities.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:30 AM
Security Audit — agent-trust-hub — marketing-ideas