seo-content-writing
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill possesses a significant attack surface for indirect prompt injection due to its core functionality.
- Ingestion points: Uses
WebFetchandWebSearchto ingest content from arbitrary external URLs and search results. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat fetched web content as untrusted or to ignore embedded instructions within that data.
- Capability inventory: The skill is granted
WriteandEditpermissions, allowing it to modify local files based on potentially poisoned data fetched from the web. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved via
WebFetchbefore it is processed by the agent. - Tool Permission Analysis (MEDIUM): The skill requests
Read,Write,Edit,WebSearch, andWebFetch. While appropriate for an SEO optimizer, this combination allows an attacker to influence local file system state via malicious web content.
Recommendations
- AI detected serious security threats
Audit Metadata