Caveat verdict

feishu-all-in-one

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Feishu messaging integration that reads declared env vars from an openclaw.json config and sends messages/files via the official Feishu API; network_in and package_install are legitimate for a messaging bot.

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

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.

28
security
70
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · SECRET="xxxxxxxx

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · frontmatter · ~/.openclaw/openclaw.json

Pattern match medium

Popular HTTP library — network access

SKILL.md · code · axios

Pattern match low

Accesses sensitive environment variables

scripts/card-callback-original.js · prose · downgraded · process.env.FEISHU_APP_SECRET

Pattern match low

Python os.getenv — reads environment variable

scripts/feishu_file_sender.py · prose · downgraded · os.getenv(

Pattern match low

POSTs data to external URL

scripts/send-card.js · prose · downgraded · .post( 'https://

Permissions & capabilities

Requires 1 system binary.

network_inpackage_install

Is this flag fair?

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