marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external file,
.claude/product-marketing-context.md, to tailor its marketing recommendations. While this allows for potential indirect prompt injection if the file contains malicious instructions, the skill has no dangerous capabilities (such as network access or command execution) to exploit. - Ingestion points:
.claude/product-marketing-context.md(via instruction to read the file). - Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: The skill is limited to providing natural language advice and mental model explanations. It contains no scripts, tools, or command execution capabilities.
- Sanitization: No sanitization is performed on the ingested text content.
- [NO_CODE]: The skill consists entirely of markdown instructions and informational content. It does not include any scripts, dependencies, or executable logic, which significantly reduces the attack surface.
Audit Metadata