Caveat verdict

knowledge-acquisition

🟢 Trusted

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

Parses content from social platforms (Xiaohongshu, WeChat, Douyin) and archives to Feishu cloud — all matching the stated knowledge management purpose with no external exfiltration of user secrets.

⚠ 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.

security

transparency

maintenance

Findings (11)

Pattern match critical

Possible hardcoded credential

README.md · code · SECRET="你的AppSecret

Pattern match high

plugins/expert/xiaohongshu.js · prose · downgraded · <script>

Pattern match high

References sudo — requests elevated privileges

README.md · code · sudo

Pattern match high

apt-get install — installs system packages

README.md · code · apt-get install

Pattern match high

yum install — installs system packages

README.md · code · yum install

Pattern match high

apk add — installs Alpine packages

README.md · code · apk add

Pattern match medium

References webhook/callback URL

README.md · code · WEBHOOK_URL

Pattern match medium

setuid — privilege escalation mechanism

index-original.js · prose · downgraded · setuid

Pattern match medium

Uses exec() — may execute shell commands

plugins/advanced/github.js · prose · downgraded · exec(

Pattern match low

Accesses sensitive environment variables

config/feishu-config.js · prose · downgraded · process.env.FEISHU_APP_SECRET

Pattern match low

Popular HTTP library — network access

DEPENDENCIES.md · prose · downgraded · axios

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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