seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external web content when auditing site URLs. This presents a potential surface for indirect prompt injection where instructions hidden in the audited site could attempt to influence the agent. (1) Ingestion points: Analyzes website content from external URLs (SKILL.md). (2) Boundary markers: The framework defines specific SEO metrics to look for, focusing the agent's attention on metadata and technical structures (SKILL.md). (3) Capability inventory: The skill references the use of web_fetch and curl to retrieve data (SKILL.md). (4) Sanitization: No specific sanitization or escaping mechanisms for the ingested web content are documented.
- [SAFE]: The skill primarily consists of instructional content and checklists for SEO best practices. It does not contain executable code, obfuscated commands, or attempts at data exfiltration.
Audit Metadata