optimizing-blog-posts-for-seo
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (MEDIUM): The skill directs the agent to ingest content from untrusted external URLs.
- Ingestion points: Step 2 ('Analyze top 5 ranking pages') and Step 6 ('Find recent statistics') in SKILL.md.
- Boundary markers: Absent. No delimiters or 'ignore' instructions are provided to mitigate adversarial instructions in external content.
- Capability inventory: SKILL.md defines a workflow for generating an 'SEO Optimization Report'. No subprocess, file-write, or network-send capabilities are explicitly used.
- Sanitization: Absent. There is no filtering or escaping of external content before processing.
Audit Metadata