primitive-inbox

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the '@primitivedotdev/cli' package globally from the NPM registry to interact with the service infrastructure.
  • [COMMAND_EXECUTION]: The skill utilizes several vendor CLI commands (e.g., 'primitive emails latest', 'primitive agent start-agent-signup') to manage inbox setup, authentication, and mail retrieval.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the following evidence chain:
  • Ingestion points: External email content is ingested into the agent context via 'primitive emails latest' and 'primitive emails wait' in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the email body.
  • Capability inventory: The agent has the capability to execute shell commands via the 'primitive' CLI and interact with external services.
  • Sanitization: There is no evidence of sanitization or filtering of the inbound email content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:32 PM
Security Audit — agent-trust-hub — primitive-inbox