seam-access-grants

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the official seam SDK using package managers like npm, pip, or bundle. These are legitimate vendor resources provided by the skill author (seamapi) for integrating their service.
  • [PROMPT_INJECTION]: The skill involves processing guest PII (name, email) and booking details to create access grants, which constitutes an indirect prompt injection surface. However, this is the primary purpose of the skill and is implemented through standard service integration patterns.
  • Ingestion points: Application code and data models containing guest and booking information.
  • Boundary markers: None explicitly defined in the instructional code snippets.
  • Capability inventory: Package installation, file system modification (writing to existing routes and models), and network access to the Seam API.
  • Sanitization: Relies on the host application's data validation and the vendor's SDK implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 04:56 PM
Security Audit — agent-trust-hub — seam-access-grants