ClawAudit verdict

web-publisher

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill publishes articles to WeChat Public Accounts. While useful, it requires configuration through a browser and interacts with an external service.

⚠ 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.

43
security
70
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (5)

Pattern match high

Possible hardcoded credential

scripts/run.js · prose · downgraded · API_KEY='${pollData.apiKey}

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API Key") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · - **数据流**： - URL 模式：CLI 把 `{url, action, theme, rewrite?}` + 你的 API Key 发给服务端；服务端自行抓取目标网页全文与图片，并发布到微信。⚠️ **服务端会接收原始 URL 并下载全文 + 图片**。 - 本地 PDF/PPTX（`draft|publi

Pattern match medium

References child_process — can spawn system processes

SKILL.md · prose · downgraded · child_process

Pattern match medium

Instructs covert action — may act without user awareness

scripts/run.js · prose · downgraded · silently

Pattern match low

Accesses sensitive environment variables

scripts/lib/credentials.js · prose · downgraded · process.env.WEB_PUBLISHER_API_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

network_incredential_access

Is this flag fair?

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