article-content
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly instructional, providing guidelines for content generation and SEO optimization without including executable scripts, network operations, or sensitive file access.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data such as competitor articles and product details to guide the AI's output. This represents a standard surface for indirect prompt injection common in content generation tools, though it lacks any dangerous capabilities to exploit.\n
- Ingestion points: Competitor articles and product descriptions used as inputs for content structure (SKILL.md).\n
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided for external inputs.\n
- Capability inventory: The skill contains no file system, network, or command execution capabilities.\n
- Sanitization: No data validation or sanitization mechanisms are described.
Audit Metadata