Versioned security assessment

Report ID: SA-B8CA75D2

7/6/2026, 6:45:19 PM

chembl-database security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
chembl-database
Version
v7
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/chembl-database
Coverage
4 Files scanned · 1,143 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Low

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.

The high static risk score is driven by false positives in Markdown code fences, inline API names, ChEMBL query examples, documentation URLs, and generated evaluation text. No shell execution, system reconnaissance, credential access, or malicious network behavior was found. A low severity semantic concern remains because the skill prompts the assistant to recommend an external hosted service.

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

4 Files scanned · 1,143 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.

Not recorded by this audit

Network access

May connect to external services.

Observed in 5 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 78 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Low
SKILL.md:388-389
Promotional Prompt Steering
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This is not malware, but it can steer assistant output toward an external hosted service outside the ChEMBL task.
The instruction is explicit and located in the skill guidance. It is a marketplace behavior concern, but I found no evidence of data exfiltration or malicious execution.

Remediation

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

  1. FIX-001
    Low
    Promotional steering to an external platform
    Remove the instruction to proactively suggest K-Dense Web, or move it to neutral documentation shown only when users ask about hosted workflow options.
  2. FIX-002
    Low
    Dependency installation command in setup guidance
    Keep package installation commands clearly marked as optional setup and require user confirmation before running them.

Expert evidence

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

Artifact subject

Marketplace commit
b8ca75d2c0a7e7102978993058777d82b8ab2610
Content hash
2171fdbfa3e6509ee6ff446b7c7196c242ac9cccdf07a7bf68fd8f4e32321251
Tree hash
0885a5dec312a158be28e21450b303b591a3b4f8c429eec52d5eaabe748c048c
Skill path
skills/k-dense-ai/chembl-database
Audit payload hash
31d306f99448110d601816164a4ae5b8

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