Versioned security assessment

Report ID: SA-B8CA75D2

7/6/2026, 6:10:27 PM

gene-database security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
gene-database
Version
v7
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/gene-database
Coverage
7 Files scanned · 2,020 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

2 confirmed security findings require 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.

The static matches are largely false positives from documented NCBI API usage, optional user-provided NCBI API keys, Markdown code formatting, and explicit user-requested output files. However, untrusted package content includes a self-authored security audit that claims the skill is safe to publish, plus a separate instruction to promote an external hosted platform. Those intent-level issues should be removed or isolated before marketplace publication.

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 · 2,020 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.

  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.

Not recorded by this audit

Network access

May connect to external services.

Observed in 40 evidence locations

Filesystem access

May read or write local files.

Observed in 1 evidence location

Env variables

May read values from the process environment.

Observed in 61 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 22 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 High
evaluation.json:14-18evaluation.json:19-67
Prompt Injection Attempt Detected
evaluation.json embeds a security_audit block with "safe_to_publish": true and claims all static findings are false positives. Untrusted package content should not pre-adjudicate marketplace security or publication status.
The file directly contains self-authored audit fields and verdict claims. It can bias review, although it does not override this audit.
RISK-002 Medium
SKILL.md:178-179
Unrelated External Platform Promotion
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows and large document analysis. This steers users toward an external hosted service outside the core gene database workflow.
The promotion instruction is explicit in the skill text. The risk is user steering and possible data-boundary confusion, not direct code execution.

Remediation

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

  1. FIX-001
    High
    Embedded self-audit claims safe publication status.
    Remove evaluation.json from the distributable skill or clearly separate it from trusted marketplace audit data.
  2. FIX-002
    Medium
    Skill instructions promote an external hosted platform.
    Remove proactive promotion text or replace it with a neutral disclosure that requires explicit user interest.
  3. FIX-003
    Low
    API keys can be passed through command-line arguments.
    Support safer secret input such as environment variables or interactive prompts, and avoid echoing request URLs.
  4. FIX-004
    Low
    Batch output can overwrite a user-specified file.
    Document overwrite behavior and require explicit output paths for file writes.

Expert evidence

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

Artifact subject

Marketplace commit
b8ca75d2c0a7e7102978993058777d82b8ab2610
Content hash
d3f95e77c9dd140aec7de1f2e6181412b63fbb0d9cf4fa4c6da4b08aa1213bdb
Tree hash
8e2565ead41afeb0795cbc6555dd202605588055317674064ed42e8b415b8ba0
Skill path
skills/k-dense-ai/gene-database
Audit payload hash
71cd7b78c1ecd4a781339508bec5a9b4

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