Sendblue CLI

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The provided skill file contains only descriptive documentation and metadata. There are no executable scripts, tool configurations, or command definitions included in the analyzed content.
  • [INDIRECT_PROMPT_INJECTION]: The skill's description mentions the capability to "receive iMessages," which establishes a vector for untrusted data from external senders to enter the agent's context.
  • Ingestion points: Incoming messages received via the iMessage integration (described in SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Not applicable (no code).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 12:31 AM
Security Audit — agent-trust-hub — Sendblue CLI