marketing-psychology

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated ingestion of external context files into the agent's prompt.
  • Ingestion points: The agent is instructed to read .agents/product-marketing-context.md or .claude/product-marketing-context.md at runtime (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within these context files.
  • Capability inventory: The skill provides textual marketing advice and analysis; it does not utilize high-privilege tools, network operations, or system-level command execution.
  • Sanitization: The content of the context files is used directly without validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:29 AM