kongctl-declarative

Warn

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains instructions for the agent to "request an unsandboxed retry" if a command is blocked by the execution environment. This is an explicit instruction to encourage bypassing security constraints or sandbox boundaries.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the kongctl CLI to manage cloud resources. This includes potentially destructive operations such as sync (which deletes unmanaged resources) and delete (which removes specified resources).
  • [EXTERNAL_DOWNLOADS]: The references/cicd-github-actions.md file provides GitHub Actions examples that download and install the vendor's own tooling from GitHub (e.g., kong/setup-kongctl@v1 and kong/setup-deck@v1).
  • [DATA_EXFILTRATION]: The troubleshooting guide in references/troubleshooting.md instructs the agent to inspect environment variables using env | grep '^KONGCTL_'. While targeted at vendor-specific configuration, this facilitates the exposure of local environment state and potential tokens.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 09:44 PM
Security Audit — agent-trust-hub — kongctl-declarative