primitive-inbox
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the @primitivedotdev/cli package from the NPM registry to provide the necessary command-line tools. This is a vendor-owned resource matching the skill author.
- [COMMAND_EXECUTION]: The skill executes shell commands to manage account authentication, signup verification, and email retrieval via the primitive CLI.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading the content of inbound emails from external senders.
- Ingestion points: Email content is retrieved via primitive emails latest and primitive emails wait in SKILL.md.
- Boundary markers: No explicit markers are defined to help the agent distinguish between system instructions and email content.
- Capability inventory: The skill allows file access, command execution, and deployment of code to the vendor platform.
- Sanitization: No specific sanitization or filtering of the email body is mentioned before the agent reads the data.
- [DYNAMIC_EXECUTION]: The skill enables the deployment of JavaScript code to the vendor's platform via primitive functions deploy to handle inbound messages automatically.
Audit Metadata