Skills
Navigate
skills/troykelly/codex-skills/code-reviewer/Gen Agent Trust Hub

code-reviewer

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data which creates a surface for indirect instructions to be passed to the agent.
  • Ingestion points: The codex-subagent command in SKILL.md accepts task context, scope, and issue/PR numbers via a shell heredoc.
  • Boundary markers: The command uses shell-level heredoc boundaries (<<'EOF'), but there are no specific prompt-level delimiters or instructions to ignore instructions embedded within the provided context.
  • Capability inventory: The skill executes the codex-subagent CLI tool as its primary function (SKILL.md).
  • Sanitization: No sanitization or input validation mechanisms are defined for the provided task context.
  • [COMMAND_EXECUTION]: The skill relies on the execution of a local CLI utility codex-subagent to perform its primary function of code review delegation (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 02:44 PM