marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read the file
.claude/product-marketing-context.mdto customize its recommendations. This introduces a surface for indirect prompt injection where malicious instructions in the context file could influence agent behavior. - Ingestion points: .claude/product-marketing-context.md.
- Boundary markers: Absent.
- Capability inventory: None (advisory text generation only).
- Sanitization: Absent.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and descriptions, with no executable scripts or code files provided.
Audit Metadata