marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hidden code, or unauthorized data access behaviors were detected. The content is strictly informational.
- [NO_CODE]: This skill is composed entirely of Markdown text and instructions for the agent; it contains no associated Python, JavaScript, or shell scripts.
- [PROMPT_INJECTION]: The skill instructs the agent to read a local file (.claude/product-marketing-context.md) to obtain product context. This represents an ingestion point for external data (Category 8: Indirect Prompt Injection). 1. Ingestion points: .claude/product-marketing-context.md referenced in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No subprocess calls, network access, or file-write operations. 4. Sanitization: Absent, as the data is used for informational context only.
Audit Metadata