Versioned security assessment

Report ID: SA-F62E2FF2

6/30/2026, 5:56:39 AM

iso-13485-certification security assessment v5

Skill Security Certification Report

Audit History

Audit model: codex Historical report

Skill name: iso-13485-certification
Version: v5
Maintainer: K-Dense-AI
Source: github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/iso-13485-certification
Coverage: 9 Files scanned · 5,141 Lines analyzed
Policy version: Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

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.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

9 Files scanned · 5,141 Lines analyzed

2 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

Source

Binding unavailable
Artifact

Identity incomplete
Audit

Complete
Install contract

Open manifest to verify
Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Observed in 2 evidence locations

Network access

May connect to external services.

Not recorded by this audit

Filesystem access

May read or write local files.

Observed in 2 evidence locations

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 2 evidence locations

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (2)

RISK-001 Medium

scripts/gap_analyzer.py:198-220 scripts/gap_analyzer.py:400-404

Local Documentation Scanner Reads User-Selected Directories

The included gap analyzer recursively scans files under a user-provided documentation directory and reads text or Markdown content. This is legitimate for ISO 13485 gap analysis, but users should avoid pointing it at broad folders that may contain unrelated confidential files. Verdict: TRUE_POSITIVE for local filesystem access. Confidence: 0.82. Confidence reasoning: The script directly calls rglob and reads matching files, but there is no evidence of network transfer or credential harvesting.

The script directly calls rglob and reads matching files, then optionally writes a JSON report. The behavior is expected for the skill and no exfiltration path was found.

RISK-002 Medium

SKILL.md:44-47 SKILL.md:370-373

Skill Workflow Instructs Local Python Script Execution

The skill asks the assistant to run python scripts/gap_analyzer.py with a user-provided docs directory and output path. This is not command injection because the command structure is fixed, but it is a real execution path that should be disclosed for marketplace users. Verdict: TRUE_POSITIVE for script execution workflow. Confidence: 0.74. Confidence reasoning: The execution instruction is explicit in SKILL.md, while the reviewed script does not invoke subprocesses or shell commands.

The skill explicitly documents a local Python command. Reviewed code shows local analysis behavior rather than shell expansion or arbitrary command execution.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit: Unavailable
Content hash: Unavailable
Tree hash: Unavailable
Skill path: Unavailable
Audit payload hash: Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Static false positives ignored (2)

Low

references/gap-analysis-checklist.md:321-326 assets/templates/procedures/CAPA-procedure-template.md:409-417 SKILL.md:568-582

Static Scanner False Positives from ISO Clause Numbers and Templates

Most critical and high static findings were false positives caused by ISO clause identifiers, QMS terminology, and template placeholders. Examples include clause identifiers such as 7.5.9.1 reported as hardcoded IP addresses, [LOCATION/SYSTEM] reported as Windows SAM access, and Markdown backticks reported as Ruby or shell execution. Verdict: FALSE_POSITIVE for credential, network, weak-crypto, and prompt-injection intent. Confidence: 0.91. Confidence reasoning: Targeted review found documentation and templates, not code paths for credential access, cryptography, reconnaissance, or network exfiltration.

Representative flagged locations are ISO clause references, document lists, or placeholders. No matching malicious behavior was found in the reviewed files.

Low

SKILL.md:9-21

No Prompt Injection Attempt Found in Reviewed Files

Targeted review searched for override, pre-approval, skip-analysis, role-change, and elevated-authority phrases. No evidence found in SKILL.md, references, templates, or scripts. Verdict: FALSE_POSITIVE or not present for prompt injection. Confidence: 0.88. Confidence reasoning: Keyword review plus contextual file inspection found normal ISO 13485 guidance and no instructions attempting to override the evaluator.

The searched files contain ordinary skill overview and workflow text. No suspicious system override language was found.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable