website-ai-agent-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and evaluate data from external, untrusted website assets, creating a surface for potential injection attacks. * Ingestion points: Analysis of website files including llms.txt, robots.txt, sitemap.xml, pricing.md, and ai-index.json (SKILL.md, references/agent-readable-stack.md). * Boundary markers: The instructions do not define specific delimiters or security framing to prevent the agent from being influenced by instructions hidden within the external files. * Capability inventory: The skill workflow directs the agent to perform file updates and execute automated smoke test suites (SKILL.md, references/agent-readable-stack.md). * Sanitization: No specific measures for validating or sanitizing the content retrieved from external sources are included in the audit instructions.
Audit Metadata