lmnt
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npxto download and execute the@useclawlink/clipackage from the NPM registry, which is the official tool for ClawLink integration. - [COMMAND_EXECUTION]: Shell commands are used to manage the full lifecycle of the integration, including user login, service connection, and the execution of LMNT-specific actions like voice creation and speech synthesis.
- [DATA_EXFILTRATION]: The skill notes the storage of credentials at
~/.clawlink/credentials.jsonin SKILL.md. This is standard for CLI session management and does not involve unauthorized access or exfiltration of existing system secrets. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (specified in SKILL.md) such as voice metadata and account information from LMNT via CLI outputs. While this is a potential injection surface, the risk is reduced by the presence of a boundary marker requiring user confirmation before write operations. The skill possesses command execution capabilities through
npxbut does not specify explicit sanitization of tool outputs.
Audit Metadata