Versioned security assessment

Report ID: SA-C8087C39

7/8/2026, 6:45:00 AM

scientific-critical-thinking security assessment v8

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
scientific-critical-thinking
Version
v8
Maintainer
davila7
Source
github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/scientific-critical-thinking
Coverage
7 Files scanned · 3,070 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.

Most static findings are false positives caused by Markdown prose, reference paths, and checklist terms. The remaining risks are a Bash-enabled schematic workflow and broad Write, Edit, and Bash permissions for a research review skill. No prompt injection text or explicit data-exfiltration intent was found in the reviewed files.

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

7 Files scanned · 3,070 Lines analyzed

3 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.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. 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.

Not recorded by this audit

Network access

May connect to external services.

Not recorded by this audit

Filesystem access

May read or write local files.

Not recorded by this audit

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 14 evidence locations

Capability review items (1)
Medium
SKILL.md:36-38
Ruby/shell backtick execution
```bash
The fenced Bash block includes a Python command that runs a local script to generate schematics. A skill that enables Bash and encourages local script execution can run unreviewed code and should require explicit user trust.

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:4
Overbroad Tool Permissions
SKILL.md grants Write, Edit, and Bash for a research appraisal skill. These capabilities allow file modification and command execution even though most review workflows only need reading user-provided material and bundled references.
The permission list is explicit in the skill header. The risk is contextual rather than evidence of malicious intent, so medium severity is appropriate.
RISK-002 Medium
SKILL.md:28-33
Default External Schematic Generation Workflow
SKILL.md tells agents to use the scientific-schematics skill and says Nano Banana Pro will automatically generate, review, and refine diagrams. It also says new documents should generate schematics by default, which may expose unpublished research content to a separate generation workflow without explicit user approval.
The text explicitly describes default schematic generation through another AI workflow. The exact data path is not defined in this skill, so confidence is high but not absolute.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Bash and file-write permissions are broader than core review needs
    Remove Bash, Write, and Edit from allowed-tools unless the skill must create files. If retained, require explicit user confirmation before commands or file writes.
  2. FIX-002
    Medium
    Local schematic command can execute project code
    Make the Python command optional, document the trusted script path, and require confirmation before running it with manuscript-derived inputs.
  3. FIX-003
    Medium
    External schematic workflow may process sensitive research content
    State whether scientific-schematics or Nano Banana Pro sends content to external services, and require approval before sharing unpublished work.

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.

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