marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill specifies reading an external file (
.claude/product-marketing-context.md) to provide context for its recommendations. - Ingestion points:
.claude/product-marketing-context.md(read via local file access). - Boundary markers: None present.
- Capability inventory: The skill is limited to providing text-based marketing advice and does not use any dangerous tools or execute shell commands.
- Sanitization: None present.
- [DATA_EXPOSURE]: The skill attempts to read a project-specific context file to tailor its output. This is a standard practice for contextual AI agents and does not target sensitive system paths or credentials.
Audit Metadata