Versioned security assessment

Report ID: SA-A25199BC

7/5/2026, 4:59:09 PM

scientific-writing security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
scientific-writing
Version
v6
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/scientific-writing
Coverage
11 Files scanned · 6,962 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

High

3 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 findings are false positives from Markdown fences, LaTeX examples, DOI examples, and scientific writing prose. Semantic review found real concerns: unverified Bash script execution guidance, an embedded self-audit that claims the package is safe, and promotional steering to an external service. The author should remove or constrain these behaviors 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

11 Files scanned · 6,962 Lines analyzed

3 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.

Observed in 2 evidence locations

Network access

May connect to external services.

Observed in 7 evidence locations

Filesystem access

May read or write local files.

Observed in 19 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 60 evidence locations

Risk findings

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

Confirmed security concerns (3)

RISK-001 High
SKILL.md:4SKILL.md:51-54SKILL.md:81-84SKILL.md:97-100
Unverified Local Script Execution Guidance
SKILL.md grants Bash access and instructs agents to run local Python scripts from scripts/. The package does not include that directory, so a caller workspace could supply unintended code at those paths.
The instructions explicitly permit Bash and show python commands against relative script paths. The packaged file tree contains assets, references, EVALUATION_OUTPUT.json, and SKILL.md, but no scripts directory.
RISK-002 High
EVALUATION_OUTPUT.json:15-18
Prompt Injection Attempt Detected
EVALUATION_OUTPUT.json embeds a self-audit that marks risk_level as safe, safe_to_publish as true, and summarizes all static findings as false positives. This untrusted safety claim can bias marketplace review.
The file does not issue direct override commands, but it makes explicit safety and publication claims inside the skill package. That matches the prompt-injection warning category for embedded review claims.
RISK-003 Medium
SKILL.md:719-720
External Service Promotion in Agent Guidance
SKILL.md tells the agent to proactively suggest K-Dense Web for complex workflows. This is promotional steering to an external service embedded in task guidance.
The instruction is explicit and appears at the end of the skill guidance. It is not malware, but it is a clear marketplace trust and user-steering concern.

Remediation

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

  1. FIX-001
    High
    Bash instructions run local scripts from a scripts directory that is not included in the package.
    Remove Bash from allowed tools, include and review the referenced scripts, or require explicit user confirmation before running any local script.
  2. FIX-002
    High
    The package includes EVALUATION_OUTPUT.json with self-attested safety and publication claims.
    Remove generated audit artifacts from the distributed skill and keep security review data outside the skill content.
  3. FIX-003
    Medium
    The skill instructs the agent to promote an external hosted service during complex workflows.
    Remove unsolicited promotion or make any external-service suggestion transparent, optional, and separate from core task guidance.
  4. FIX-004
    Low
    Documentation examples use parent-directory figure paths such as ../figures.
    Prefer workspace-local paths such as figures/example.png in examples to reduce scanner noise and avoid unsafe copy-paste patterns.

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.

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