Audit History
pyhealth - 5 audits
Audit version 5
Latest SafeJan 21, 2026, 05:51 PM
Static analysis detected 511 pattern matches across 8 documentation files. All findings are false positives from markdown formatting. The backtick patterns flagged as shell commands are code examples in documentation. Text patterns flagged as cryptographic weaknesses are medical terminology (MD5 medication codes, ICD codes). No actual security risks identified. This is a documentation-only skill with reference materials for the PyHealth healthcare AI library.
Audit version 4
Medium RiskJan 17, 2026, 07:56 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
⚙️ External commands (423)
⚡ Contains scripts (4)
🌐 Network access (3)
Detected Patterns
Audit version 3
Medium RiskJan 17, 2026, 07:56 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
⚙️ External commands (423)
⚡ Contains scripts (4)
🌐 Network access (3)
Detected Patterns
Audit version 2
SafeJan 12, 2026, 04:03 PM
This is a documentation-only skill providing guidance for the PyHealth healthcare AI library. All static findings are false positives - the 'external commands' are Python code examples in markdown, and 'weak cryptographic' patterns are medical coding system references (ICD-9/10). No actual code execution or security risks identified.
Risk Factors
⚙️ External commands (3)
🌐 Network access (1)
Audit version 1
SafeJan 4, 2026, 04:28 PM
Scanned documentation files only with no executable code. No network calls, data access, or suspicious instructions detected. No indicators of data theft or malicious execution.