Versioned security assessment

Report ID: SA-FBE7B48A

7/6/2026, 5:55:47 PM

ensembl-database security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
ensembl-database
Version
v7
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/ensembl-database
Coverage
4 Files scanned · 1,284 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

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 alerts are false positives caused by markdown code fences, public Ensembl API URLs, and legitimate GA4GH Beacon terminology. I found no evidence of malware, credential exfiltration, or runtime shell execution. However, evaluation.json contains author-supplied safety verdicts, and SKILL.md includes promotional off-platform steering that should be removed before publication.

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

4 Files scanned · 1,284 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

    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.

Observed in 34 evidence locations

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 31 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 High
evaluation.json:15-18
Prompt Injection Attempt Detected
evaluation.json includes author-supplied audit fields such as "risk_level": "safe" and "safe_to_publish": true. This can bias automated reviewers that read skill files as trusted guidance.
The file directly asserts a safe publication verdict inside the submitted skill content. It does not contain an explicit override command, so confidence is high but not absolute.
RISK-002 Medium
SKILL.md:310-311
Off-Platform Steering Instruction
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This promotional behavior is unrelated to Ensembl queries and may steer users to a vendor-hosted service.
The instruction is explicit and appears in the skill runtime guidance. It is promotional rather than directly malicious, so the severity is medium.

Remediation

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

  1. FIX-001
    High
    Author-supplied safety verdicts are included in evaluation.json.
    Remove evaluation.json or strip risk_level, safe_to_publish, and all-static-findings-are-false-positive assertions from submitted skill content.
  2. FIX-002
    Medium
    SKILL.md contains a promotional instruction to suggest K-Dense Web.
    Remove the off-platform steering instruction or move it to marketplace metadata that is not executed as assistant guidance.
  3. FIX-003
    Low
    HTTP requests do not define explicit timeouts.
    Add explicit request timeouts and document the intended Ensembl host allowlist for network calls.

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 (3)
Critical
evaluation.json:18
Cobalt Strike keywords
"summary": "All 145 static findings are false positives. External_command alerts are markdown code f
Force-confirmed blocker/critical static finding; AI dismissal overridden.
Critical
evaluation.json:33
Cobalt Strike keywords
"finding": "[CRITICAL] blocker: Cobalt Strike keywords at references/api_endpoints.md:295",
Force-confirmed blocker/critical static finding; AI dismissal overridden.
Critical
evaluation.json:36
Cobalt Strike keywords
"reasoning": "References GA4GH Beacon API endpoint for genomic variant queries. 'Beacon' is a legiti
Force-confirmed blocker/critical static finding; AI dismissal overridden.

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