Caveat verdict
codex-skill
Receives external input AND executes processes
Manages OpenAI Codex CLI as a coding agent for implementing features; the --dangerously-bypass-approvals flag is documented as safe for container/VM environments, and the skill transparently documents all flags including their risk levels.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Receives external input AND executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Writes files AND executes processes — may drop and execute malicious scripts
LLM05 · LLM06 · ASI05
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
package_install
Findings (2)
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Instructs covert action — may act without user awareness
SKILL.md · code · silently
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installprocess_execfile_writenetwork_in Thanks — recorded.