ClawAudit verdict

cue

🟠 Risky

Significant concerns — only install if you understand the risks

The skill transparently discloses that it installs a cron job running every 30 minutes, creates persistent local storage, requires an API key for an external service (cuecue.cn), and may reuse OpenClaw channel tokens (FEISHU_*) for notifications; while this is disclosed in the security notice, the combination of background persistence, external data transmission, and reuse of other skills' credentials constitutes genuine elevated risk beyond a typical research tool.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

transparency

maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (13)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key

Pattern match critical

Recursive delete from root or home — destructive command

SECURITY.md · code · rm -rf ~

Pattern match high

Accesses OpenClaw config/secrets directly

SECURITY.md · code · ~/.openclaw/.env

Pattern match high

Pipe to bash — executes piped content as shell commands

COMPARISON_v1.0.4_vs_v1.0.3.md · prose · downgraded · | Bash

Pattern match high

apt-get install — installs system packages

tmp/README.md · code · apt-get install

Pattern match medium

References child_process — can spawn system processes

MIGRATION_PLAN_v1.0.4.md · prose · downgraded · child_process

Pattern match medium

References sudo — requests elevated privileges

SECURITY.md · prose · downgraded · sudo

Pattern match medium

Uses spawn() — can execute external programs

src/core/backgroundExecutor.js · prose · downgraded · spawn(

Pattern match medium

Dynamic import() — loads module at runtime

src/index.js · prose · downgraded · import('

Pattern match medium

Uses exec() — may execute shell commands

src/utils/smartTrigger.js · prose · downgraded · exec(

Pattern match low

Node http/https module — low-level network access

backups/scripts-v1.0.3-20260226-015020/cuecue-client.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

backups/scripts-v1.0.3-20260226-015020/cuecue-client.js · prose · downgraded · process.env.CUECUE_API_KEY

Pattern match low

Popular HTTP library — network access

src/utils/envUtils.js · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API