The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on npx @insforge/cli to perform all diagnostic operations. This is a standard pattern for using vendor-provided tooling and is appropriate for the skill's role as a debugging assistant.
[DATA_EXFILTRATION]: The skill provides commands to access sensitive project data, including source code (functions code), database records (db query), and secrets (secrets get). These capabilities are documented as part of the troubleshooting process for InsForge environments and do not include instructions to transmit this data to external or unauthorized destinations.
[PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection via the diagnose --ai command, which processes user-provided issue descriptions, and various log-reading commands. While these inputs could potentially contain malicious instructions, the skill does not exhibit any direct signs of exploitation, and the use of boundaries within the CLI tool provides standard operational security.

insforge-debug