seo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
web_fetchandcurlto retrieve content from external websites for auditing purposes. It also references well-known and trusted external services, including Google Search Console, PageSpeed Insights, and the Google Rich Results Test. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes untrusted data from third-party websites during the audit process.
- Ingestion points: Website HTML and metadata retrieved via
web_fetchorcurl(referenced in SKILL.md). - Boundary markers: The instructions do not define clear delimiters or specific directives for the agent to disregard potential commands found within the fetched website content.
- Capability inventory: The agent uses
web_fetchto acquire data for analysis. - Sanitization: There is no evidence of content sanitization, escaping, or filtering before the data is processed by the agent.
Audit Metadata