Skip to content

resend — CLI Agent Evaluation

Evaluated against the CLI Agent Spec — a specification defining 74 failure modes for CLI tools used under AI agent orchestration.

CLI version: resend-cli v2.8.1 Evaluated: 2026-07-06 Scope: Critical (22 of 74 failure modes)

Note: this run covered the 22 Critical failure modes as scoped at evaluation time. §75 (Safe-Default Execution Mode Absent), a Critical mode added in the same cycle, was not evaluated.

Scores

Metric Result
Failure mode score 1.2/3 — 4 passing · 12 partial · 5 failing
Readiness score 14/15 [A]
Observed bugs 6 confirmed during live evaluation
Worst gaps §1 Exit Codes, §25 Prompt Injection, §43 Output Size, §64 Headless GUI, §74 Credential Scopes

Key Findings

  • whoami can report a fake flag-provided key as authenticated, so credential presence can be mistaken for validity.
  • Browser-opening commands still invoke the OS opener even in quiet/JSON contexts and do not emit a structured URL fallback.
  • Dry-run output can include large file contents verbatim with no truncation metadata or output cap.
  • User-provided HTML is returned without an untrusted-content marker, creating prompt-injection risk for agents.
  • Resend is strong on proactive readiness: it ships a co-versioned agent skill, detailed references, workflows, and a JSON command tree.

Files

File What it is
report-index.md Full scorecard — all failure modes, readiness breakdown, links to all reports
report-issues.md Concrete bugs and gaps agents will hit when using this CLI as-is
report-runtime.md Compact operational brief — what to set, what to avoid, what to watch for
report-agent-dev.md Integration guide — invocation invariants and per-gap workarounds for agent developers
report-dev.md Fix list for CLI authors — what to implement, mapped to spec requirements
findings.md Raw scorecard — one row per evaluated failure mode
issues.md Observed bugs recorded during live evaluation
trace.md Audit trail — exact check commands, exit codes, stdout/stderr per §N
environment.md CLI environment profile — binary path, version, flags, timeout method
readiness.md Proactive readiness scores across 5 dimensions

Generated by cli-agent-audit · CLI Agent Spec