Caveat verdict

aws-wechat-article-writing

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill accesses and sends API keys to external endpoints, which could potentially be used for malicious purposes.

⚠ 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.

68
security
80
transparency
70
maintenance

Findings (3)

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md) 的产物,由 review 调用 `write

Pattern match medium

Accesses cloud provider credentials

SKILL.md · prose · downgraded · ~/.aws

Pattern match low

Python urllib.request — network access

scripts/write.py · prose · downgraded · urllib.request

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: WRITING_MODEL_API_KEY). Requires 1 system binary.

Is this flag fair?

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