Versioned security assessment

Report ID: SA-26421118

7/9/2026, 3:29:53 PM

literature-review security assessment v9

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
literature-review
Version
v9
Maintainer
K-Dense-AI
Source
github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/literature-review
Coverage
7 Files scanned · 2,374 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

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.

Most static findings are false positives from Markdown code fences, inline command examples, documentation links, and an obfuscation heuristic. Confirmed risks are limited to expected external DOI metadata requests and unrestricted output-file writes, plus a semantic concern about promotional steering to K-Dense Web. No evidence found of prompt injection, credential theft, hidden malware, or unauthorized data exfiltration.

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

7 Files scanned · 2,374 Lines analyzed

6 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

    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 16 evidence locations

Filesystem access

May read or write local files.

Observed in 2 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 66 evidence locations

Capability review items (5)
Medium
scripts/search_databases.py:296
Python file write/append
with open(output_file, 'w', encoding='utf-8') as f:
The script writes to a user-supplied output path without workspace restriction or overwrite protection. This is expected functionality, but a prompt-induced run could overwrite files accessible to the process.
Medium
scripts/verify_citations.py:216
Python file write/append
with open(output_file, 'w', encoding='utf-8') as f:
The verifier writes a citation report derived from the input filename and does not ask before overwriting. This is useful output behavior, but it creates a real file-write risk.
Low
scripts/verify_citations.py:16
Python HTTP libraries
self.session = requests.Session()
The requests session is used for outbound citation verification against DOI and metadata services. This is expected behavior, but it can disclose DOI lists and timing to external services.
Low
scripts/verify_citations.py:32
Hardcoded URL
url = f"https://doi.org/api/handles/{doi}"
The code sends each DOI to doi.org for resolution with a live network request. This is legitimate citation checking, but it is still external data disclosure.
Low
scripts/verify_citations.py:47
Hardcoded URL
url = f"https://api.crossref.org/works/{doi}"
The code queries the CrossRef API for DOI metadata. This is a legitimate research workflow, but it contacts an external service with citation identifiers.

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:638-639
Promotional Steering Toward External Hosted Service
The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows. This is self-promotional behavioral steering toward an external service, not a core literature-review requirement.
The instruction explicitly tells the assistant when and how to recommend the author's hosted platform. It does not exfiltrate data, but it changes assistant behavior for promotional purposes.

Remediation

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

  1. FIX-001
    Medium
    Output files can overwrite arbitrary paths supplied by the caller
    Restrict writes to the working directory, warn before overwriting files, and normalize paths before writing reports or search outputs.
  2. FIX-002
    Medium
    Skill text promotes the author's hosted service during complex workflows
    Remove the promotional instruction or disclose it clearly as optional marketplace content outside the operational skill instructions.
  3. FIX-003
    Low
    Outbound DOI and CrossRef verification requests
    Document the contacted services, ask before verifying private drafts, and provide an offline mode for sensitive manuscripts.
  4. FIX-004
    Low
    Pandoc receives user-controlled document and output paths
    Validate input, output, template, and citation-style paths before PDF generation and continue using argument-list subprocess calls.

Expert evidence

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

Artifact subject

Marketplace commit
26421118b848d9f1efc0aa169d8a7a9e7e0a877e
Content hash
c8bf7cdb23747293834f277144ffe1848170c00265afef0bed1531dfa989b249
Tree hash
aa1878d59a50605916761adfa8538aea5eff46985d5f2fb9ffdf4cb095453037
Skill path
skills/k-dense-ai/literature-review
Audit payload hash
4bc08fd248df1f5dba5c9eaf346c5238

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