Skills research-lookup

📦

research-lookup

Name: research-lookup
Author: davila7

Content revision r2 Medium Risk 🔑 Env variables🌐 Network access⚙️ External commands

Research Current Literature with Cited Sources

Finding current scholarly evidence and reliable citations takes time. This skill queries Perplexity Sonar through OpenRouter and organizes results with source links.

Supports: Claude Codex Code(CC)

⚠️ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "research-lookup" from https://skillstore.io/skills/davila7-research-lookup.md and its manifest at https://skillstore.io/api/skills/davila7-research-lookup/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-research-lookup.md Signed manifest GET /api/skills/davila7-research-lookup/manifest Signed lockfile GET /api/skills/davila7-research-lookup/lockfile

Test it

Using "research-lookup". Find recent peer-reviewed studies on off-target effects in CRISPR gene editing.

Expected outcome:

A concise summary of recurring findings and reported mitigation strategies.
Key studies grouped by method, publication date, and evidence strength.
Source links, DOI details, limitations, and open research questions.

Using "research-lookup". Compare transformer models and recurrent neural networks for clinical time-series analysis.

Expected outcome:

A structured comparison of accuracy, data needs, interpretability, and computational cost.
Areas of agreement and conflict across recent studies.
Cited sources with verification links and cautions about study quality.

Security Audit

Medium Risk

v9 • 7/23/2026 Open versioned report

The skill reads one documented API key and performs expected HTTPS requests to OpenRouter. Most high-severity detections are key names, placeholders, or text references, not hardcoded secrets or environment-file reads. Queries leave the local system, and SKILL.md recommends one nonbundled generator command that requires explicit dependency review.

Files scanned

1,704

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

research_lookup.py:113-155 scripts/research_lookup.py:113-155

Research Queries Sent to a Third Party

The full research query is embedded in a prompt and sent to OpenRouter for Perplexity processing. Sensitive queries therefore leave the local environment.

Lines 113-155 interpolate the query into messages and pass them to the request helper, so the disclosure path is explicit.

Capability review items (19)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:38-40

Ruby/shell backtick execution

```bash

Lines 38-40 contain a Bash command invoking scripts/generate_schematic.py, which is absent from this skill. A same-named workspace script could execute without package-level review.

Low

examples.py:135

Python getenv function

if not os.getenv("OPENROUTER_API_KEY"):

The example checks the documented OPENROUTER_API_KEY before live use. Scope is limited, but this is real access to a secret-bearing environment variable.

Low

examples.py:135

getenv function call

if not os.getenv("OPENROUTER_API_KEY"):

The example checks the documented OPENROUTER_API_KEY before live use. Scope is limited, but this is real access to a secret-bearing environment variable.

Low

lookup.py:58

Python getenv function

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Low

lookup.py:58

getenv function call

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Low

research_lookup.py:155

HTTP client library

response = self._make_request(messages, model)

This call triggers the OpenRouter request containing the research query. It is core functionality, but user-provided query content leaves the local system.

Low

research_lookup.py:102

Python HTTP libraries

response = requests.post(

This POST sends the research messages and bearer credential to the documented OpenRouter HTTPS endpoint. The transmission is expected, but it is real outbound network access.

Low

research_lookup.py:305

Python HTTP libraries

response = requests.get(

This GET contacts OpenRouter's models endpoint with the configured authentication headers. The destination is expected, but the outbound request is real.

Low

research_lookup.py:44

Python getenv function

self.api_key = os.getenv("OPENROUTER_API_KEY")

The client reads the documented OPENROUTER_API_KEY into memory for OpenRouter authentication. This is expected behavior, but it is real credential access.

Low

research_lookup.py:330

Python getenv function

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Low

research_lookup.py:44

getenv function call

self.api_key = os.getenv("OPENROUTER_API_KEY")

The client reads the documented OPENROUTER_API_KEY into memory for OpenRouter authentication. This is expected behavior, but it is real credential access.

Low

research_lookup.py:330

getenv function call

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Low

scripts/research_lookup.py:155

HTTP client library

response = self._make_request(messages, model)

This call triggers the OpenRouter request containing the research query. It is core functionality, but user-provided query content leaves the local system.

Low

scripts/research_lookup.py:102

Python HTTP libraries

response = requests.post(

This POST sends the research messages and bearer credential to the documented OpenRouter HTTPS endpoint. The transmission is expected, but it is real outbound network access.

Low

scripts/research_lookup.py:305

Python HTTP libraries

response = requests.get(

This GET contacts OpenRouter's models endpoint with the configured authentication headers. The destination is expected, but the outbound request is real.

Low

scripts/research_lookup.py:44

Python getenv function

self.api_key = os.getenv("OPENROUTER_API_KEY")

The client reads the documented OPENROUTER_API_KEY into memory for OpenRouter authentication. This is expected behavior, but it is real credential access.

Low

scripts/research_lookup.py:330

Python getenv function

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Low

scripts/research_lookup.py:44

getenv function call

self.api_key = os.getenv("OPENROUTER_API_KEY")

The client reads the documented OPENROUTER_API_KEY into memory for OpenRouter authentication. This is expected behavior, but it is real credential access.

Low

scripts/research_lookup.py:330

getenv function call

if not os.getenv("OPENROUTER_API_KEY"):

The entry point reads the documented OPENROUTER_API_KEY for a preflight check. It accesses only that variable, so the security impact is low.

Risk Factors

🔑 Env variables (37)

🌐 Network access (20)

⚙️ External commands (31)

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-research-lookup/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-research-lookup/security.svg)](https://skillstore.io/skills/davila7-research-lookup?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-research-lookup?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-research-lookup/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-research-lookup.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). research-lookup security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-research-lookup/audits/9

BibTeX citation

@techreport{davila7-davila7-research-lookup-2026,
  author = {davila7},
  title = {research-lookup security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-research-lookup/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "research-lookup security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-research-lookup/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-research-lookup:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

K-Dense-AI Recommended

k-dense-ai-research-lookup

Skillstore Score 50

Evidence Confidence High

Skillstore usage 52

Updated

2026-08-21

davila7 Current

davila7-research-lookup

Skillstore Score 50

Evidence Confidence High

Skillstore usage 35

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Prepare a Literature Review

Find recent studies, key findings, and source links before drafting a literature review.

Verify Technical Claims

Check claims and gather citation details for manuscripts, reports, or technical documentation.

Compare Research Evidence

Compare evidence, methods, limitations, and unresolved questions across several studies.

Try These Prompts

Find Recent Studies

Find peer-reviewed studies about [topic] published since [year]. Summarize the main findings and list source links with DOI details.

Verify a Research Claim

Check this claim against recent scholarly evidence: [claim]. State whether evidence supports it and identify conflicting findings.

Compare Methods or Findings

Compare [approach A] and [approach B] for [use case]. Evaluate effectiveness, limitations, study quality, and important trade-offs with citations.

Build a Critical Evidence Synthesis

Synthesize research on [question] using studies from [date range]. Separate consensus, conflicting evidence, methodological weaknesses, and research gaps. Include verification links.

Best Practices

Use precise topics, date ranges, populations, and requested evidence types.
Remove confidential, personal, or unpublished information before submitting a query.
Open each cited source and verify its metadata, methods, and claimed findings.

Avoid

Do not treat generated citations or summaries as verified evidence.
Do not submit broad questions without a field, time frame, or research objective.
Do not use the output alone for medical, legal, safety, or policy decisions.