敏感内容扫描器
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a local sensitive-content scanner with no artifact-backed evidence of exfiltration or hidden behavior, but users should protect generated reports because they may summarize sensitive findings.
This skill looks appropriate for local document scanning. Before installing or using it, confirm you are comfortable running a local Python script on the selected files, keep generated reports private, and verify any optional Crypto dependency if you use encrypted dictionary files.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A generated report may expose sensitive findings if it is stored in a shared folder or forwarded to others.
The scanner saves a report containing scan results. Even if PII is masked, the report can reveal where sensitive content exists.
扫描完成后，会生成 **HTML 格式报告** ... 默认生成 `report.html` ... 扫描报告建议保存
Run scans only on intended files, store reports in a private location, and delete or protect reports after review.
The script will read the selected document files and generate local output.
The skill is implemented as a local Python script. Local execution is expected for this scanner, but users should understand that code runs on their machine.
python3 scan_sensitive.py 文档.docx
Use the bundled script only from the trusted skill package and review command arguments before running it on sensitive documents.
Encrypted dictionary mode may fail or require a locally installed crypto library whose provenance users should verify.
The optional encrypted-dictionary loader depends on a Crypto package, but the skill has no install spec declaring dependencies.
from Crypto.Cipher import AES
If using encrypted dictionaries, install dependencies from trusted package sources and avoid running untrusted dictionary files.