seo-audit
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill directs the agent to crawl and analyze external, untrusted web content which represents a vulnerability surface for indirect prompt injection attacks. An attacker could place malicious instructions in meta tags, content, or robots.txt files to manipulate the agent's behavior.\n
- Ingestion points: Website HTML content, robots.txt, and XML sitemaps referenced in the Audit Framework and Technical SEO Audit sections.\n
- Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions within the ingested data.\n
- Capability inventory: The skill itself is declarative, but the instructions assume an agent with web browsing and document reading capabilities.\n
- Sanitization: Absent. There is no mention of filtering or sanitizing external content before the agent processes it for the audit report.
Audit Metadata