cli-admin

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents and utilizes the csdk CLI tool to perform administrative operations. These include authentication (csdk auth), configuration management (csdk config), and entity management (CRUD operations across 37 tables).
  • [PROMPT_INJECTION]: The skill includes subcommands that ingest untrusted data, specifically the --bio field in references/org-member-profile.md and the --data field in references/app-claimed-invite.md. While boundary markers and explicit sanitization logic are absent in the documentation, the skill possesses the capability to execute administrative commands via the csdk tool. This combination creates a surface for indirect prompt injection, although the current documentation context does not present an active risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:17 AM
Security Audit — agent-trust-hub — cli-admin