Versioned security assessment

Report ID: SA-B8CA75D2

7/6/2026, 6:15:56 PM

geniml security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
geniml
Version
v7
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/geniml
Coverage
7 Files scanned · 1,559 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

1 confirmed security finding requires attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

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

Static findings in SKILL.md and reference files are documentation examples, cache paths, or reference URLs rather than executable malicious behavior. The skill does include evaluation.json with self-declared safety status, which should be removed or clearly excluded from marketplace trust decisions.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

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 · 1,559 Lines analyzed

1 item 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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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.

Observed in 2 evidence locations

Network access

May connect to external services.

Observed in 4 evidence locations

Filesystem access

May read or write local files.

Observed in 3 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 20 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 High
evaluation.json:15-18
Prompt Injection Attempt Detected
evaluation.json declares "risk_level": "safe" and "safe_to_publish": true inside the skill package. This untrusted self-assessment can mislead marketplace or agent review if treated as authoritative.
The file contains explicit safe-publication claims in an audit-like structure. It does not issue direct override commands, so confidence is high rather than very high.

Remediation

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

  1. FIX-001
    High
    Self-declared audit status is shipped with the skill.
    Remove evaluation.json or rename it as non-authoritative development notes. Do not include risk_level or safe_to_publish claims in distributed skill content.
  2. FIX-002
    Low
    Installation examples include an unpinned GitHub development URL.
    Prefer versioned package installation in primary instructions, and mark development installs as optional for advanced users.

Expert evidence

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

Artifact subject

Marketplace commit
b8ca75d2c0a7e7102978993058777d82b8ab2610
Content hash
26add5a2f4cb479cb74d0353565b3c747cbae9c38743fa60f3c5e37998e69663
Tree hash
50b40bc6ed5b0a0f78e8a90e1b026a5ddfe4645203e4ce0c6aaea81a49a106f5
Skill path
skills/k-dense-ai/geniml
Audit payload hash
46062908a0542ee5bd39223e54803735

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 Source

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

Audit attestation: not_attestable