servicem8
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and execute the@useclawlink/clipackage from the official NPM registry. - [COMMAND_EXECUTION]: The skill operates by executing shell commands to manage authentication and perform data operations on Servicem8.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for external data from Servicem8, which presents a surface for indirect prompt injection.
- Ingestion points: Data retrieved from Servicem8 via the
runandactionscommands (SKILL.md). - Boundary markers: The instructions include a clear directive: "Reads first; confirm with the user before any write."
- Capability inventory: The skill can read, describe, and execute actions (write) in Servicem8 through the vendor CLI (SKILL.md).
- Sanitization: The skill relies on mandatory user confirmation as a manual sanitization gate before state-changing actions are performed.
Audit Metadata