marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a directive to read a specific local file for product marketing context if it exists.
- Ingestion points:
.claude/product-marketing-context.md(referenced in SKILL.md). - Boundary markers: None specified within the skill instructions for this file read.
- Capability inventory: The skill performs only text generation and analysis; it contains no file-writing, network, or command execution capabilities.
- Sanitization: None specified. This represents a minor surface for indirect prompt injection if the context file contains malicious instructions, but is otherwise standard behavior for context-aware tools.
Audit Metadata