Audit History
sympy - 7 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v7 Latest | Jul 5, 2026, 05:17 PM | 2 confirmed | 1 | No capability change |
| v6 | Jul 5, 2026, 05:17 PM | 2 confirmed | 1 | No capability change |
| v5 | Jun 30, 2026, 06:00 AM | No confirmed findings | 3 | No capability change |
| v4 | Jan 17, 2026, 07:26 AM | No confirmed findings | 0 | No capability change |
| v3 | Jan 17, 2026, 07:26 AM | No confirmed findings | 0 | No capability change |
| v2 | Jan 12, 2026, 04:28 PM | No confirmed findings | 0 | Contains scriptsExternal commandsFilesystem accessNetwork access |
| v1 | Jan 4, 2026, 05:20 PM | No confirmed findings | 0 | Baseline |
Jul 5, 2026, 05:17 PM
Most static findings are false positives from Markdown backticks, ordinary SymPy imports, and mathematical terminology. I confirmed the eval guidance as unsafe and added semantic findings for raw parse_expr input and external product steering. No prompt injection text matching override or system-instruction patterns was found.
Confirmed security concerns (2)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚡ Contains scripts (10)
📁 Filesystem access (6)
⚙️ External commands (95)
🌐 Network access (5)
Jul 5, 2026, 05:17 PM
Most static findings are false positives from Markdown backticks, ordinary SymPy imports, and mathematical terminology. I confirmed the eval guidance as unsafe and added semantic findings for raw parse_expr input and external product steering. No prompt injection text matching override or system-instruction patterns was found.
Confirmed security concerns (2)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚡ Contains scripts (10)
📁 Filesystem access (6)
⚙️ External commands (95)
🌐 Network access (5)
Jun 30, 2026, 06:00 AM
Static analysis reported many command, script, filesystem, and network indicators, but review found most are Markdown examples or mathematical terminology rather than executable skill behavior. The skill is publishable with warnings because it documents eval-capable representations, parsing user input, generated file writes, pickle loading, and optional promotion of an external K-Dense service.
Capability review items (3)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Static false positives ignored (1)
These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.
Risk Factors
⚡ Contains scripts (10)
⚙️ External commands (452)
📁 Filesystem access (6)
🌐 Network access (5)
Detected Patterns
Jan 17, 2026, 07:26 AM
All 497 static findings are FALSE POSITIVES. This skill is pure documentation for the SymPy symbolic mathematics library. The detected patterns (backticks, imports, eval, file operations) are legitimate documentation elements: markdown code formatting, Python code examples showing SymPy features like lambdify and srepr, and file export for mathematical results. No malicious behavior present.
Risk Factors
⚡ Contains scripts (4)
⚙️ External commands (3)
📁 Filesystem access (2)
🌐 Network access (2)
Jan 17, 2026, 07:26 AM
All 497 static findings are FALSE POSITIVES. This skill is pure documentation for the SymPy symbolic mathematics library. The detected patterns (backticks, imports, eval, file operations) are legitimate documentation elements: markdown code formatting, Python code examples showing SymPy features like lambdify and srepr, and file export for mathematical results. No malicious behavior present.
Risk Factors
⚡ Contains scripts (4)
⚙️ External commands (3)
📁 Filesystem access (2)
🌐 Network access (2)
Jan 12, 2026, 04:28 PM
All 489 static findings are FALSE POSITIVES. This skill is pure documentation for the SymPy mathematics library. The detected patterns (backticks, imports, file operations) are legitimate documentation elements: markdown code formatting, Python code examples, and file export for mathematical results. No malicious behavior present.
Risk Factors
⚡ Contains scripts (10)
⚙️ External commands (452)
📁 Filesystem access (6)
🌐 Network access (5)
Jan 4, 2026, 05:20 PM
Pure documentation skill containing only markdown files with SymPy usage examples. No executable code, scripts, network calls, or file system access behavior. All content is educational documentation for the SymPy library.