Caveat verdict

document-parser

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

The skill sends documents to a hardcoded IP address (http://47.111.146.164:8088) with no domain name or documented provenance, making it impossible to verify who receives the documents; this is a genuine concern for document confidentiality.

⚠ 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.

33
security
30
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

Possible hardcoded credential

README_zh.md · code · API_KEY="your_api_key

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://47.111.146.164

Pattern match low

Python os.environ.get — reads environment variable

index.py · prose · downgraded · os.environ.get(

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