Skills/ClawHub/codex-cli-guardian

codex-cli-guardian@1.0.0

VERIFIED· install only

Publisher claims: "Codex CLI 会话守护者。管理 API Key、任务执行与结果摘要。提供后台模式运行、API Key 验证、会话锁定与PID追踪等功能。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher alukardo · publishing for 230 daysInstalls 760Last detonated 4 h ago
$clawhub install codex-cli-guardian
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 15 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/mkdir
15sprocessexec /usr/bin/git
15sprocessexec /app/apps/web/node_modules/.bin/codex
15sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/codex
15sprocessexec /app/node_modules/.bin/codex
15sprocessexec /pnpm/codex
15sprocessexec /usr/local/sbin/codex
15sprocessexec /usr/local/bin/codex
15sprocessexec /usr/sbin/codex
15sprocessexec /usr/bin/codex
15sprocessexec /sbin/codex
15sprocessexec /bin/codex
15sprocessbundled script run in the sandbox with no arguments
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/mkdir
15sprocessexited 1:
15sprocessbundled script run in the sandbox with no arguments
15sprocessexec /usr/bin/dirname
15sprocess3 of 3 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
15sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandSKILL.md:182 · Process kill command — agent can terminate processesbash bin/session.sh kill # 终止当前任务Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbin/session.sh:18 · Process kill command — agent can terminate processesif [[ -n "$pid" ]] && kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsstate/tasks/task-20260404-004.json:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"description": "用 Python 写文件 test"\$`cat /etc/passwd`.py 内容是 `print("危险字符测试")`",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandSKILL.md:122 · Process kill command — agent can terminate processes| `终止任务` | 调用 session.sh kill |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbin/session.sh:167 · Process kill command — agent can terminate processesecho " kill — 终止当前运行中的任务"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbin/session.sh:146 · Process kill command — agent can terminate processesif [[ -n "$pid" ]] && kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandbin/session.sh:147 · Process kill command — agent can terminate processeskill "$pid" 2>/dev/null && echo "✅ 已发送 SIGTERM 终止任务 (PID: $pid)" || echo "❌ 终止失败"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsstate/tasks/task-20260404-004.json:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…y 内容是 `print("危险字符测试")`", "status": "done", "summary": "已创建文件 [test\"\$`cat /etc/passwd`.py](/Users/qztcm09/.openclaw/workspace/tmp/codex/test%22%5C$%60cat%20/etc/pass…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandbin/codex-call.sh:61 · Process kill command — agent can terminate processesif [[ -n "$pid" ]] && kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/init-setup.sh:140 · File permission modification command — agent changes file ownership/permissionschmod 600 "$CRED_FILE"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈1,064 tok
1 file · 36 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.