everything-seo
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to audit external website resources, including page content, robots.txt files, and sitemaps. This represents a potential surface for indirect prompt injection if the agent audits a malicious website containing hidden instructions.\n
- Ingestion points: Processes external data from web pages, robots.txt, and XML sitemaps as part of the Phase 1 Audit.\n
- Boundary markers: The skill does not define specific delimiters to wrap external content or provide explicit instructions for the agent to ignore potentially malicious embedded content within the analyzed pages.\n
- Capability inventory: There are no scripts, subprocess calls, or network operation tools included within the skill itself; it relies on the agent's base capabilities.\n
- Sanitization: No instructions are provided for sanitizing or validating external content before it is processed by the agent.
Audit Metadata