Audit History
molfeat - 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, 04:58 PM | 1 confirmed | 0 | No capability change |
| v6 | Jul 5, 2026, 04:58 PM | 1 confirmed | 0 | No capability change |
| v5 | Jun 30, 2026, 05:19 AM | 1 confirmed | 1 | No capability change |
| v4 | Jan 17, 2026, 06:34 AM | No confirmed findings | 0 | No capability change |
| v3 | Jan 17, 2026, 06:34 AM | No confirmed findings | 0 | No capability change |
| v2 | Jan 12, 2026, 04:03 PM | No confirmed findings | 0 | External commandsFilesystem accessNetwork access |
| v1 | Jan 5, 2026, 04:07 PM | No confirmed findings | 0 | Baseline |
Jul 5, 2026, 04:58 PM
Most static findings are false positives caused by Markdown code fences, inline API names, local cache examples, and documentation links. No prompt injection attempt, data exfiltration intent, or automatic command execution was found. The only semantic concern is unsafe pickle cache loading guidance without a trust warning.
Confirmed security concerns (1)
Risk Factors
📁 Filesystem access (2)
⚙️ External commands (75)
🌐 Network access (4)
Jul 5, 2026, 04:58 PM
Most static findings are false positives caused by Markdown code fences, inline API names, local cache examples, and documentation links. No prompt injection attempt, data exfiltration intent, or automatic command execution was found. The only semantic concern is unsafe pickle cache loading guidance without a trust warning.
Confirmed security concerns (1)
Risk Factors
📁 Filesystem access (2)
⚙️ External commands (75)
🌐 Network access (4)
Jun 30, 2026, 05:19 AM
Static analysis reported many high-risk patterns, but review found they are mostly false positives from markdown code formatting and chemistry terminology. No prompt injection, credential exfiltration, or malicious execution path was found; the main publishable warning is example code that loads pickle cache files.
Confirmed security concerns (1)
Needs review findings (1)
These findings came from uncertain legacy audit verdicts, so they require review but are not counted as confirmed security issues.
Static false positives ignored (3)
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
⚙️ External commands (3)
📁 Filesystem access (2)
🌐 Network access (1)
Detected Patterns
Jan 17, 2026, 06:34 AM
The molfeat skill is a legitimate cheminformatics library for molecular feature extraction. All 397 static findings are false positives triggered by scientific terminology in documentation. The scanner misinterpreted markdown code fences as shell commands, chemistry terminology (ecfp, maccs, gin, c2) as security threats, and documentation URLs as network indicators.
Risk Factors
⚙️ External commands (1)
📁 Filesystem access (1)
🌐 Network access (1)
Jan 17, 2026, 06:34 AM
The molfeat skill is a legitimate cheminformatics library for molecular feature extraction. All 397 static findings are false positives triggered by scientific terminology in documentation. The scanner misinterpreted markdown code fences as shell commands, chemistry terminology (ecfp, maccs, gin, c2) as security threats, and documentation URLs as network indicators.
Risk Factors
⚙️ External commands (1)
📁 Filesystem access (1)
🌐 Network access (1)
Jan 12, 2026, 04:03 PM
The molfeat skill is a legitimate cheminformatics library for molecular feature extraction. All static analysis findings are false positives - the flagged patterns are documentation examples showing legitimate scientific computing commands, not security threats.
Risk Factors
⚙️ External commands (1)
📁 Filesystem access (1)
🌐 Network access (1)
Jan 5, 2026, 04:07 PM
Pure documentation skill with no executable code. Contains only markdown documentation and JSON configuration files describing the molfeat Python library. No network calls, file system access beyond its own directory, environment variable access, or command execution capabilities detected.