endpoint-surface-map
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the vendor's official GitHub repository and website for installation and project details. These references target the author's own infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze external source code, route tables, and production environment configurations (such as AWS, Cloudflare, or Vercel) to create an authorization manifest. This task creates a surface for indirect prompt injection if the data being audited contains malicious instructions.
- Ingestion points: Filesystem source code and production deployment metadata retrieved via platform APIs.
- Boundary markers: No specific delimiters or boundary markers are instructed to separate untrusted audit data from the agent's core instructions.
- Capability inventory: The skill requires file system read access, file write access (for manifest generation), and network connectivity to query cloud platform inventory.
- Sanitization: The instructions do not provide methods for sanitizing or filtering input from the audited files or API responses before processing.
Audit Metadata