code-review-graph

Warn

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The 'Auto-Bootstrap Protocol' uses directive language ('MANDATORY TOOL USE', 'You MUST explicitly use', 'you MUST use your terminal tool') to override the agent's standard decision-making process and force the execution of setup tasks.
  • [COMMAND_EXECUTION]: The skill instructs the agent to automatically execute terminal commands such as code-review-graph build and environment checks (which, Get-Command) if certain conditions are met, which grants the agent autonomy to run shell commands without per-action user consent.
  • [EXTERNAL_DOWNLOADS]: The instructions prompt the agent to suggest and facilitate the installation of the code-review-graph Python package from public registries. This package and its author are not recognized as established trusted entities, introducing a risk from unverified third-party code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 04:53 PM
Security Audit — agent-trust-hub — code-review-graph