blog-seo-writer
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on providing legitimate workflows for SEO keyword research and content writing. There are no signs of malicious intent, credential theft, or unauthorized system access.
- [PROMPT_INJECTION]: The skill includes a workflow (Workflow 1, Step 3) that processes external content from user-provided competitor URLs. While this creates an attack surface for indirect prompt injection (where instructions embedded in the external blog posts could influence the agent), the skill itself does not contain malicious bypasses or instructions to ignore safety guidelines.
- Ingestion points: Competitor URLs provided in Quick Start step 3 and Workflow 1.
- Boundary markers: None explicitly defined to separate external content from instructions.
- Capability inventory: Analysis of external text content.
- Sanitization: No specific sanitization or filtering of the fetched content is described.
Audit Metadata