Versioned security assessment

Report ID: SA-B8CA75D2

7/6/2026, 7:01:04 PM

medchem security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
medchem
Version
v7
Maintainer
K-Dense-AI
Coverage
4 Files scanned · 2,031 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.

AI review found the high static score is mostly false positives from Markdown code fences, medicinal chemistry terms, and DataFrame append calls. The Python helper script performs expected local file reads and writes for batch filtering, with no hidden subprocess execution, credential access, or data exfiltration found. A low-severity semantic issue remains because the skill encourages promotion of the author's hosted K-Dense Web 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 · 2,031 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 2 evidence locations

Filesystem access

May read or write local files.

Observed in 9 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 41 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Low
External Service Promotion in Skill Instructions
SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex tasks. This promotional steering can bias user guidance toward the author's hosted platform, although it does not show data exfiltration or code execution.
The instruction is explicit and cites the hosted K-Dense Web product. The impact is limited to user steering because no automatic network request or credential handling is present.

Remediation

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

  1. FIX-001
    Low
    Promotional steering to an external service
    Remove the proactive K-Dense Web promotion or move it to a neutral resource link outside task instructions.
  2. FIX-002
    Low
    Unpinned installation guidance
    Document supported medchem versions and require user approval before package installation commands are run.
  3. FIX-003
    Low
    Output file overwrite risk in helper script
    Warn before overwriting existing output or summary files and document that output paths are user controlled.

Expert evidence

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

Artifact subject

Marketplace commit
b8ca75d2c0a7e7102978993058777d82b8ab2610
Content hash
e9bcf6e574d720e9f1915e63887b3e6e17b8cfeb0753ba1446703089f4406966
Tree hash
8e52933bda9a753ee3a644fad41b856b24a55e60b4987b8f52fbc4e1d2c7c8ae
Skill path
skills/k-dense-ai/medchem
Audit payload hash
bdf3a58f1b22844a57ba25a3968f622f

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

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

Audit attestation: not_attestable