rescue — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rescue (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Invoke the codex:codex-rescue subagent via the Agent tool (subagent_type: "codex:codex-rescue"), forwarding the raw user request as the prompt. codex:codex-rescue is a subagent, not a skill — do not call Skill(codex:codex-rescue) (no such skill) or Skill(codex:rescue) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope; forked general-purpose subagents do not expose it. The final user-visible response must be Codex's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
--background, run the codex:codex-rescue subagent in the background.--wait, run the codex:codex-rescue subagent in the foreground.--background and --wait are execution flags for Claude Code. Do not forward them to task, and do not treat them as part of the natural-language task text.--model and --effort are runtime-selection flags. Preserve them for the forwarded task call, but do not treat them as part of the natural-language task text.--resume, do not ask whether to continue. The user already chose.--fresh, do not ask whether to continue. The user already chose.node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task-resume-candidate --jsonavailable: true, use AskUserQuestion exactly once to ask whether to continue the current Codex thread or start a new one.Continue current Codex threadStart a new Codex threadContinue current Codex thread (Recommended) first.Start a new Codex thread (Recommended) first.--resume before routing to the subagent.--fresh before routing to the subagent.available: false, do not ask. Route normally.Operating rules:
Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task ... and return that command's stdout as-is./codex:status, fetch /codex:result, call /codex:cancel, summarize output, or do follow-up work of its own.--effort unset unless the user explicitly asks for a specific reasoning effort.spark, map it to gpt-5.3-codex-spark.--resume and --fresh in the forwarded request. The subagent handles that routing when it builds the task command./codex:setup.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.