Skills perplexity-search

📦

perplexity-search

Name: perplexity-search
Author: davila7

Content revision r2 High Risk 🌐 Network access🔑 Env variables⚙️ External commands📁 Filesystem access

Search the Live Web with Perplexity

Static model knowledge cannot cover current research and recent events. This skill queries Perplexity through OpenRouter and returns web-grounded answers with citations.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

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

Agent request

Review the Skillstore skill "perplexity-search" from https://skillstore.io/skills/davila7-perplexity-search.md and its manifest at https://skillstore.io/api/skills/davila7-perplexity-search/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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-perplexity-search.md Signed manifest GET /api/skills/davila7-perplexity-search/manifest Signed lockfile GET /api/skills/davila7-perplexity-search/lockfile

Test it

Using "perplexity-search". What changed in AlphaFold 3 research during the past year?

Expected outcome:

A dated summary of recent findings, reported benchmarks, limitations, and source citations.

Using "perplexity-search". Compare current evidence for two diabetes interventions using randomized trials.

Expected outcome:

A structured comparison of outcomes, study quality, safety findings, disagreements, and links to the cited sources.

Security Audit

High Risk

v9 • 7/23/2026 Open versioned report

Most static findings are documentation examples, placeholders, Markdown backticks, and expected environment access. Confirmed risks include credential exposure, shell-profile modification, executable .env loading, and unrestricted output paths. Search queries are transmitted to third-party providers, so sensitive input requires review.

Files scanned

2,010

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (4)

High

references/openrouter_setup.md:108

Environment file access

source .env

The documented source command treats .env as executable shell code. Any injected command in that file runs with the user's privileges.

High

SKILL.md:45-47 scripts/setup_env.py:125-127

API Key Accepted Through Command Arguments

The documented setup workflow places the API key in --api-key, exposing it through process listings and shell history.

The quick-start command places a key placeholder after --api-key, and the parser explicitly accepts that secret-bearing argument.

Medium

scripts/setup_env.py:31-51

New Secret Files May Have Broad Permissions

The setup helper creates a plaintext API-key file with default process permissions and does not enforce owner-only access.

The file is opened with the standard text write API, and no chmod or restrictive creation mode appears before the complete key is written.

Medium

scripts/perplexity_search.py:95-105

Search Queries Leave the Local Environment

The complete user query is sent through LiteLLM to OpenRouter and Perplexity. Sensitive research, personal data, or proprietary text may reach third parties.

The completion call sends the query as the user message to an OpenRouter Perplexity model, which is the skill's declared operation.

Capability review items (13)

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

High

references/openrouter_setup.md:71

Hidden file in home directory

echo 'export OPENROUTER_API_KEY="sk-or-v1-your-key-here"' >> ~/.bashrc

The setup instructions append the API credential to a shell startup file. This persists a plaintext secret and modifies code executed for future shells.

High

references/openrouter_setup.md:72

Hidden file in home directory

source ~/.bashrc

The instructions source the user's shell profile, immediately executing every command in that file. Unexpected profile content would run with the user's privileges.

High

references/openrouter_setup.md:75

Hidden file in home directory

echo 'export OPENROUTER_API_KEY="sk-or-v1-your-key-here"' >> ~/.zshrc

The setup instructions append the API credential to a shell startup file. This persists a plaintext secret and modifies code executed for future shells.

High

references/openrouter_setup.md:76

Hidden file in home directory

source ~/.zshrc

The instructions source the user's shell profile, immediately executing every command in that file. Unexpected profile content would run with the user's privileges.

High

references/openrouter_setup.md:227

Generic API/secret keys

echo $OPENROUTER_API_KEY

The troubleshooting command prints the complete OPENROUTER_API_KEY to terminal output. Logs, screen sharing, or shell capture could expose the credential.

High

scripts/setup_env.py:51

Generic API/secret keys

f.write(f'OPENROUTER_API_KEY={api_key}\n')

The setup helper writes the complete API key to a plaintext file without enforcing restrictive permissions. A newly created file may be readable by other local users.

High

scripts/setup_env.py:157

Generic API/secret keys

print(f" export OPENROUTER_API_KEY={args.api_key}")

The setup helper prints the complete API key in an export command. Terminal logs, captured output, or shared screens can disclose the credential.

Medium

references/openrouter_setup.md:71

Hidden file access

echo 'export OPENROUTER_API_KEY="sk-or-v1-your-key-here"' >> ~/.bashrc

The command writes a persistent API-key export into the user's bash startup file. This stores a secret in plaintext and changes future shell behavior.

Medium

references/openrouter_setup.md:72

Hidden file access

source ~/.bashrc

The command reads and executes the user's bash startup file in the current shell. This has broader effects than loading one declared environment value.

Medium

references/openrouter_setup.md:75

Hidden file access

echo 'export OPENROUTER_API_KEY="sk-or-v1-your-key-here"' >> ~/.zshrc

The command writes a persistent API-key export into the user's zsh startup file. This stores a secret in plaintext and changes future shell behavior.

Medium

references/openrouter_setup.md:76

Hidden file access

source ~/.zshrc

The command reads and executes the user's zsh startup file in the current shell. This has broader effects than loading one declared environment value.

Medium

scripts/perplexity_search.py:269

Python file write/append

with open(args.output, 'w') as f:

The script opens the user-selected output path in truncating write mode without path restrictions or no-clobber protection. It can overwrite any user-writable file.

Medium

scripts/setup_env.py:44

Python file write/append

with open(env_path, 'w') as f:

The user-controlled --env-file path is opened in truncating write mode. The helper can overwrite any user-writable file while preserving only line-based content.

Risk Factors

🌐 Network access (19)

assets/.env.example:5 references/openrouter_setup.md:324 references/openrouter_setup.md:339 scripts/perplexity_search.py:43 scripts/setup_env.py:77 scripts/setup_env.py:121 SKILL.md:36 SKILL.md:254 SKILL.md:285 SKILL.md:293 SKILL.md:386 SKILL.md:387 SKILL.md:388 SKILL.md:389 SKILL.md:390 SKILL.md:393 SKILL.md:394 SKILL.md:395 SKILL.md:398

🔑 Env variables (50)

⚙️ External commands (50)

references/openrouter_setup.md:79 references/openrouter_setup.md:80 references/openrouter_setup.md:85 SKILL.md:41-47 SKILL.md:47-50 SKILL.md:50-52 SKILL.md:52-55 SKILL.md:55-57 SKILL.md:57-59 SKILL.md:59-64 SKILL.md:64-66 SKILL.md:66-69 SKILL.md:69-71 SKILL.md:71-74 SKILL.md:74-76 SKILL.md:76-79 SKILL.md:79-81 SKILL.md:81-85 SKILL.md:85-94 SKILL.md:94-95 SKILL.md:95-96 SKILL.md:96-97 SKILL.md:97-98 SKILL.md:98-100 SKILL.md:100-141 SKILL.md:141-147 SKILL.md:147-151 SKILL.md:151-155 SKILL.md:155-159 SKILL.md:159-163 SKILL.md:163-167 SKILL.md:167-171 SKILL.md:171-175 SKILL.md:175-179 SKILL.md:179-183 SKILL.md:183-189 SKILL.md:189-191 SKILL.md:191-207 SKILL.md:207-211 SKILL.md:211-218 SKILL.md:218-224 SKILL.md:224-237 SKILL.md:237-250 SKILL.md:250-251 SKILL.md:251-252 SKILL.md:252-253 SKILL.md:253-264 SKILL.md:264-268 SKILL.md:268-275 SKILL.md:275-277

📁 Filesystem access (16)

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-perplexity-search/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-perplexity-search.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). perplexity-search security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-perplexity-search/audits/9

BibTeX citation

@techreport{davila7-davila7-perplexity-search-2026,
  author = {davila7},
  title = {perplexity-search security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-perplexity-search/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: "perplexity-search security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-perplexity-search/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-perplexity-search: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-perplexity-search

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 21

Updated

2026-08-21

davila7 Current

davila7-perplexity-search

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Review Recent Research

Find recent papers, reported findings, and citations for a defined scientific question.

Check Current Technical Guidance

Locate recent documentation, implementation advice, and ecosystem changes beyond static model knowledge.

Compare Emerging Developments

Summarize recent products, policies, or market changes with dated supporting sources.

Try These Prompts

Find Current Information

Find the latest reliable information about [topic]. Use sources from the past [period], summarize the answer, and list citations.

Search Recent Literature

Find peer-reviewed research about [question] published since [date]. Report study types, main findings, limitations, and source citations.

Compare Current Options

Compare [option A] and [option B] for [context]. Use recent evidence, explain tradeoffs, identify disagreements, and cite each major claim.

Synthesize Conflicting Evidence

Investigate [claim] across primary sources, reviews, and official guidance. Separate established facts, disputed conclusions, evidence gaps, and dated citations.

Best Practices

Include a precise topic, time range, domain, and preferred source types.
Choose the least expensive model that matches the query complexity and set a token limit.
Open important citations and verify dates, claims, methods, and source quality before reuse.

Avoid

Do not send secrets, personal data, unpublished research, or proprietary text in a query.
Do not treat generated summaries or citation lists as verified evidence.
Do not use advanced search models for simple facts without considering cost.