Audit History
iso-13485-certification - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | Jul 9, 2026, 03:25 PM | No confirmed findings | 0 | No capability change |
| v8 | Jul 9, 2026, 03:25 PM | No confirmed findings | 0 | No capability change |
| v7 | Jul 5, 2026, 06:09 PM | No confirmed findings | 1 | No capability change |
| v6 | Jul 5, 2026, 06:09 PM | No confirmed findings | 1 | Env variables Contains scripts |
| v5 | Jun 30, 2026, 05:56 AM | 2 confirmed | 0 | Contains scriptsExternal commands |
| v4 | Jan 17, 2026, 07:53 AM | No confirmed findings | 0 | No capability change |
| v3 | Jan 17, 2026, 07:53 AM | No confirmed findings | 0 | Contains scripts |
| v2 | Jan 12, 2026, 04:33 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 4, 2026, 04:41 PM | No confirmed findings | 0 | Baseline |
Jul 9, 2026, 03:25 PM
Manual review found the static alerts are false positives caused by ISO 13485 terminology, markdown file references, and an explicit local report writer. No prompt injection, hidden network access, credential access, or unauthorized command execution was found in the reviewed files.
Risk Factors
🔑 Env variables (69)
📁 Filesystem access (1)
⚙️ External commands (26)
Jul 9, 2026, 03:25 PM
Manual review found the static alerts are false positives caused by ISO 13485 terminology, markdown file references, and an explicit local report writer. No prompt injection, hidden network access, credential access, or unauthorized command execution was found in the reviewed files.
Risk Factors
🔑 Env variables (69)
📁 Filesystem access (1)
⚙️ External commands (26)
Jul 5, 2026, 06:09 PM
Static analysis was dominated by false positives from ISO 13485 vocabulary, Markdown backticks, and normal documentation references. I confirmed one medium issue: gap_analyzer.py writes to a user-supplied output path without an overwrite guard. No evidence found of prompt injection, credential access, network calls, or malicious intent.
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
🔑 Env variables (69)
📁 Filesystem access (1)
⚙️ External commands (26)
Jul 5, 2026, 06:09 PM
Static analysis was dominated by false positives from ISO 13485 vocabulary, Markdown backticks, and normal documentation references. I confirmed one medium issue: gap_analyzer.py writes to a user-supplied output path without an overwrite guard. No evidence found of prompt injection, credential access, network calls, or malicious intent.
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
🔑 Env variables (69)
📁 Filesystem access (1)
⚙️ External commands (26)
Jun 30, 2026, 05:56 AM
AI review dismissed the static critical and high alerts as false positives from ISO clause numbers, Markdown formatting, and QMS template placeholders. The skill is publishable with a medium warning because it includes a local Python gap analyzer that reads user-selected documentation folders and can write a JSON report.
Confirmed security concerns (2)
Static false positives ignored (2)
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 (2)
📁 Filesystem access (2)
⚙️ External commands (2)
Detected Patterns
Jan 17, 2026, 07:53 AM
All 416 static findings are false positives. The scanner misinterpreted documentation keywords in markdown templates as security issues (e.g., 'SAM' as Windows Security Accounts Manager, cryptographic terms in QMS documentation). This is a legitimate ISO 13485 documentation toolkit containing templates and a local Python analysis script with no network access or credential handling.
Risk Factors
📁 Filesystem access (1)
Jan 17, 2026, 07:53 AM
All 416 static findings are false positives. The scanner misinterpreted documentation keywords in markdown templates as security issues (e.g., 'SAM' as Windows Security Accounts Manager, cryptographic terms in QMS documentation). This is a legitimate ISO 13485 documentation toolkit containing templates and a local Python analysis script with no network access or credential handling.
Risk Factors
📁 Filesystem access (1)
Jan 12, 2026, 04:33 PM
This is a legitimate ISO 13485 documentation toolkit for medical device manufacturers. All 404 static findings are FALSE POSITIVES caused by pattern matching on documentation content. The Python script only reads/writes files locally and performs keyword analysis. No network access, credential access, or command execution.
Risk Factors
⚡ Contains scripts (1)
📁 Filesystem access (2)
Jan 4, 2026, 04:41 PM
Legitimate ISO 13485 documentation toolkit. Contains one local Python script that scans user-provided documents for compliance keywords and generates reports. No network calls, no credential access, no environment harvesting. All file I/O is scoped to user-specified directories. Fully consistent with stated documentation assistance purpose.