content-marketing
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a directory listing command to identify installed companion skills and provide relevant recommendations.
- [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing additional components from external sources using a package manager to expand functionality.
- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by processing untrusted user-provided marketing briefs and product data. 1. Ingestion points: User-supplied text for content strategy and blog generation (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Environment discovery via directory listing commands (SKILL.md). 4. Sanitization: No validation or sanitization routines are implemented for external inputs.
Audit Metadata