sendgrid-automation

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it processes untrusted external data that can influence agent behavior without adequate security controls.
  • Ingestion points: Untrusted data enters the agent context through contact imports (SENDGRID_IMPORT_CONTACTS), contact updates (SENDGRID_ADD_OR_UPDATE_A_CONTACT), and campaign creation (SENDGRID_CREATE_SINGLE_SEND) as described in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters used to separate user-provided data from system instructions or to warn the agent against executing commands found within the processed data.
  • Capability inventory: The skill provides access to powerful tools including email delivery (SENDGRID_CREATE_SINGLE_SEND), contact management (SENDGRID_ADD_OR_UPDATE_A_CONTACT), and data deletion (SENDGRID_REMOVE_LIST_AND_OPTIONAL_CONTACTS) listed in SKILL.md.
  • Sanitization: The instructions do not describe any mechanisms for validating, escaping, or filtering external content before it is processed by the tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:34 AM
Security Audit — agent-trust-hub — sendgrid-automation