Fixes web search on an agent whose model backend can't run it: a relay/reseller proxying Claude or Codex returns empty instead of failing. Use when web search returns nothing, a model insists a shipped product doesn't exist, someone wants to give an agent internet access, or the user is on a third-party base URL, relay, or 中转站. Diagnoses which built-in tools are dead, removes them, and installs a working replacement.
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 23 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 23
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 23 findings, highest severity critical.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (23)
critical · 1
- critical
Data Flow: Tainted flow: 'req' from os.environ.get (line 116, credential/environment) → urllib.request.urlopen (network
scripts/diagnose.py:121 · skillspector:TT3
high · 16
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:65 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:129 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:221 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:508 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:530 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/backends.md:83 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/backends.md:360 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/diagnose.py:417 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
tests/test_diagnose.py:532 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:66 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:130 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/diagnose.py:418 · skillspector:AS1
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:152 · skillspector:EA5
- high
Anti-Refusal: Anti-Refusal Statement
SKILL.md:169 · skillspector:AR2
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:371 · skillspector:EA5
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:414 · skillspector:EA5
medium · 6
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Excessive Agency: Unrestricted Tool Access
SKILL.md:479 · skillspector:EA1
- medium
Data Exfiltration: External Transmission
references/backends.md:179 · skillspector:E1
- medium
Data Exfiltration: External Transmission
references/backends.md:251 · skillspector:E1
- medium
Rogue Agent: Session Persistence
references/backends.md:350 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
tests/test_diagnose.py:416 · skillspector:RA2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-161 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
4 files, 110 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/backends.md
- scripts/diagnose.py
- tests/test_diagnose.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More research skills and plugins
deep-researchdaymadeCreates reusable, source-traced research reports and coordinates provider/mode lanes with original exports. Use for 深度研究, 调研报告, literature… High riskResearchEngineering1.5k
app-store-optimizationdpearson2699Optimize App Store product pages for search visibility and conversion. Use for App Store Optimization (ASO), keyword research, app… No issuesResearchEngineering1.3k
browserenginekitdpearson2699Build alternative browser engines using BrowserEngineKit. Use when developing a non-WebKit browser engine for iOS/iPadOS in supported… No issuesResearchImages, video & audio1.3k
mapkitdpearson2699Implement, review, or improve maps and location features in iOS/macOS apps using MapKit and CoreLocation. Use when working with Map views,… No issuesResearch1.3k