signup
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security vulnerabilities detected. The skill is purely instructional and follows best practices for providing AI agent personas.
- [PROMPT_INJECTION]: Indirect prompt injection risk was evaluated due to the skill reading project context files for marketing data.
- Ingestion points: Reads .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md from the project directory.
- Boundary markers: None specified in the instructions.
- Capability inventory: None. The skill does not utilize any tools or execute shell commands.
- Sanitization: None.
- Note: This represents an attack surface but is assessed as safe because the skill lacks the capabilities to perform dangerous actions based on the ingested content.
Audit Metadata