seo-audit
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs site audits by fetching and analyzing external web content using platform tools like
web_fetchorcurl. This creates a vulnerability surface where untrusted data from a website could contain hidden instructions intended to hijack the agent's logic. - Ingestion points: External website content retrieved during audits as instructed in
SKILL.md. - Boundary markers: The instructions lack specific guidance on using delimiters or protective system prompts to isolate external content from the agent's core instructions.
- Capability inventory: The skill utilizes web fetching tools and reads local project context files (e.g.,
.agents/product-marketing.md). - Sanitization: There is no mention of filtering or sanitizing fetched content before it is incorporated into the agent's context.
Audit Metadata