lumail
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill initiates the download of the
lumailpackage from the npm registry usingnpx. This is the intended method for providing the agent with the necessary tools to interact with the Lumail service. - [REMOTE_CODE_EXECUTION]: The skill executes the
lumailCLI during setup (npx lumail@latest setup --authenticate) and authentication tests. As this is a vendor-provided tool required for the skill's primary function, it is considered normal operational behavior. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external format guides for campaigns and workflows using the
get_skilltool, creating a surface where third-party data influences the agent's output. - Ingestion points: Format guides fetched via the
get_skilltool (referenced in SKILL.md). - Boundary markers: Absent; the skill does not specify delimiters for the fetched content.
- Capability inventory: The agent uses the ingested data to generate campaign bodies and configure workflow graphs.
- Sanitization: No explicit sanitization or validation of the fetched guides is mentioned.
Audit Metadata