seo-programmatic
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as URLs, CSV/JSON files, and API structures, which serves as an ingestion point for untrusted content.
- Ingestion points: User-provided URLs and data sources referenced in the 'Data Source Assessment' and 'URL Pattern Strategy' sections of SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or instructions to treat external data as untrusted text, increasing the risk of the agent following instructions embedded in the analyzed content.
- Capability inventory: The skill instructions are analytical and do not invoke dangerous tools for file modification or network exfiltration.
- Sanitization: No sanitization or escaping mechanisms are defined for the data processed during the SEO audit.
Audit Metadata