skills/majiayu000/spellbook/codex/Gen Agent Trust Hub

codex

Warn

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the codex CLI with high-impact flags, including --sandbox danger-full-access and --full-auto. These flags grant the external tool broad system access and autonomous editing capabilities.
  • [COMMAND_EXECUTION]: Instructions in SKILL.md mandate appending 2>/dev/null to shell commands by default. This suppresses the standard error stream, which prevents the user from seeing security warnings, tool errors, or indicators of unexpected behavior during execution.
  • [COMMAND_EXECUTION]: The skill recommends a shell piping pattern (echo "prompt" | codex ...) for processing user input. This construction is vulnerable to command injection if the agent does not rigorously escape special shell characters within the user-provided prompt.
  • [COMMAND_EXECUTION]: The skill explicitly instructs the agent to always use the --skip-git-repo-check flag, which bypasses the tool's built-in safety checks regarding the state and location of the repository being analyzed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 03:58 PM
Security Audit — agent-trust-hub — codex