中文 EN

Scan Report

Scan New Files

⚠ Low Risk — Risk Score 15/100
Last scan:21 hr ago Rescan
15 /100
deepread-pii
DeepRead PII Redaction - Redact PII from documents using AI-powered context-aware detection
Pure documentation skill describing external API integration for PII redaction. No malicious code or hidden functionality detected; all behavior is clearly documented.
Skill Namedeepread-pii
Duration25.4s
Enginepi
✓
Safe to install
This skill is safe to use. Ensure users understand that documents are uploaded to deepread.tech for processing (privacy consideration). No implementation files exist beyond documentation.

Findings 2 items

Severity Finding Location
Low
External data upload clearly documented Doc Mismatch
Documents are uploaded to api.deepread.tech for processing. This is prominently disclosed in the documentation and security notes section.
This skill instructs the agent to POST your file to https://api.deepread.tech
→ Users should be aware that sensitive documents leave their environment. No action required as behavior is disclosed.
 SKILL.md:1
Low
Example API keys in documentation Doc Mismatch
SKILL.md contains sk_live_your_key_here (line 49) and sk_live_YOUR_KEY (line 369) as example placeholders. These are clearly example values, not real credentials.
API_KEY="sk_live_your_key_here"
→ No action needed — these are clearly example placeholders in documentation examples.
 SKILL.md:49
ResourceDeclaredInferredStatusEvidence
Filesystem READ NONE ✓ Aligned SKILL.md documents file upload capability but no code exists to exercise it
Network READ NONE ✓ Aligned SKILL.md describes API calls but no implementation code exists
Shell NONE NONE — No shell commands in documentation
Environment READ NONE ✓ Aligned DEEPREAD_API_KEY access declared in metadata; no code present
2 High 18 findings
🔑
High API Key 疑似硬编码凭证
API_KEY="sk_live_your_key_here"
SKILL.md:49
🔑
High API Key 疑似硬编码凭证
API_KEY = "sk_live_YOUR_KEY"
SKILL.md:369
🔗
Medium External URL 外部 URL
https://www.deepread.tech
SKILL.md:5
🔗
Medium External URL 外部 URL
https://api.deepread.tech
SKILL.md:21
🔗
Medium External URL 外部 URL
https://www.deepread.tech/privacy
SKILL.md:29
🔗
Medium External URL 外部 URL
https://www.deepread.tech/dashboard
SKILL.md:41
🔗
Medium External URL 外部 URL
https://www.deepread.tech/dashboard/?utm_source=clawhub
SKILL.md:44
🔗
Medium External URL 外部 URL
https://api.deepread.tech/v1/pii/redact
SKILL.md:73
🔗
Medium External URL 外部 URL
https://your-app.com/webhooks/pii
SKILL.md:76
🔗
Medium External URL 外部 URL
https://api.deepread.tech/v1/pii/550e8400-e29b-41d4-a716-446655440000
SKILL.md:100
🔗
Medium External URL 外部 URL
https://...(signed
SKILL.md:122
🔗
Medium External URL 外部 URL
https://api.deepread.tech/v1/pii/JOB_ID
SKILL.md:466
🔗
Medium External URL 外部 URL
https://api.deepread.tech/v1/process
SKILL.md:478
🔗
Medium External URL 外部 URL
https://api.deepread.tech/v1/form-fill
SKILL.md:510
🔗
Medium External URL 外部 URL
https://www.deepread.tech/dashboard/billing?utm_source=clawhub
SKILL.md:588
📧
Info Email 邮箱地址
[email protected]
SKILL.md:229
📧
Info Email 邮箱地址
[email protected]
SKILL.md:230
📧
Info Email 邮箱地址
[email protected]
SKILL.md:639

File Tree

1 files · 20.0 KB · 643 lines
Markdown 1f · 643L
└─ 📝 SKILL.md Markdown 643L · 20.0 KB

Security Positives

✓ No executable code present — this is a pure documentation skill
✓ All external API calls to api.deepread.tech are clearly documented
✓ Security notes section explicitly addresses data handling and privacy
✓ Privacy policy link provided for user review
✓ No credential harvesting beyond user's own API key
✓ No obfuscation, base64, or anti-analysis techniques
✓ No filesystem modifications or system file access
✓ No suspicious network connections beyond declared API endpoint