agent-email-cli

Warn

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @zaddy6/agentemail package globally using npm or bun. This is an external dependency from a source that is not verified or well-known.
  • [COMMAND_EXECUTION]: The skill uses shell commands for environment setup, package installation, and managing the email CLI tool.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it retrieves data from disposable email inboxes, which are untrusted external sources.
  • Ingestion points: The agent-email read and agent-email show commands in SKILL.md ingest message summaries and full bodies into the agent context.
  • Boundary markers: Absent. No instructions are provided to delimit email content or warn the agent against executing instructions contained within the messages.
  • Capability inventory: The agent can execute shell commands, manage local files via the CLI, and perform network requests through the package manager.
  • Sanitization: No sanitization or validation of the retrieved email content is performed before processing or summarization.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 08:07 AM
Security Audit — agent-trust-hub — agent-email-cli