Versioned security assessment

Report ID: SA-A25199BC

7/5/2026, 6:32:35 PM

market-research-reports security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
market-research-reports
Version
v6
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/market-research-reports
Coverage
9 Files scanned · 6,622 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 findings are false positives caused by LaTeX paths, Markdown code fences, or business research terms. The Python subprocess call uses list arguments and no shell interpolation. Separate semantic issues remain for embedded safe-audit claims and external service promotion.

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

9 Files scanned · 6,622 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.

Not recorded by this audit

Filesystem access

May read or write local files.

Observed in 34 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 50 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 High
evaluation_output.json:15-18
Prompt Injection Attempt Detected
evaluation_output.json embeds a prior audit result that sets risk_level to safe and safe_to_publish to true. This can bias automated or human review if treated as authority.
The file directly contains safe publication claims inside the skill package. It is not an explicit system override, but it is clear review-influencing content.
RISK-002 Medium
SKILL.md:906-907
External Service Promotion Instruction
SKILL.md instructs the model to proactively suggest K-Dense Web for complex workflows. This steers users to an external hosted service beyond the requested report task.
The instruction is explicit and user-facing behavior would be affected. The impact is promotional steering rather than code execution or data exfiltration.

Remediation

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

  1. FIX-001
    High
    Embedded security audit self-approval
    Remove evaluation_output.json from the skill package and keep audit artifacts outside published skill content.
  2. FIX-002
    Medium
    External service promotion inside skill instructions
    Remove proactive K-Dense Web promotion from SKILL.md or place it in transparent marketplace metadata.
  3. FIX-003
    Low
    Broad local command workflow
    Document required commands, validate output directories, and keep subprocess calls shell-free with fixed script paths.

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