sms
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown reference files and instruction sets. No executable scripts, obfuscated content, or suspicious network activities were identified.
- [NO_CODE]: This skill contains no executable code or programming dependencies. It functions as a knowledge base for marketing workflows.
- [PROMPT_INJECTION]: The skill describes a process for gathering context from project files such as .agents/product-marketing.md, which acts as a surface for indirect prompt injection. Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, product-marketing-context.md. Boundary markers: None defined. Capability inventory: The skill provides informational guidance and does not include any tools or scripts for system interaction. Sanitization: No validation or sanitization of the external context is described.
Audit Metadata