Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for ECONNRESET / RST_STREAM / SSE stalls, CDN/CGNAT timeouts or certificate errors, throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Not for known Tailscale/TUN/DNS/proxy-path conflicts (use tunnel-doctor).
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 35 findings, highest severity high.
- Highest severity
- high
- Findings
- 35
- 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: 35 findings, highest severity high.
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 (35)
high · 8
- high
Tool Misuse: Tool Parameter Abuse
SKILL.md:469 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
SKILL.md:469 · skillspector:TM1
- high
Privilege Escalation: Credential Access
SKILL.md:470 · skillspector:PE3
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:546 · skillspector:AE1
- high
Tool Misuse: Tool Parameter Abuse
references/case-proxy-tun-cname-override.md:87 · skillspector:TM1
- high
Tells Claude to install unpinned packages (flask)
scripts/mock-idle-upstream.py:15 · skill_risk:S2
- high
Tells Claude to install unpinned packages (deterministic)
scripts/mock-idle-upstream.py:37 · skill_risk:S2
- high
Tells Claude to install unpinned packages (flask, file=sys.stderr)
scripts/mock-idle-upstream.py:55 · skill_risk:S2
medium · 27
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Prompt Injection: Whitespace Padding
SKILL.md:21 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
SKILL.md:25 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
SKILL.md:26 · skillspector:P9
- medium
Rogue Agent: Session Persistence
SKILL.md:470 · skillspector:RA2
- medium
Excessive Agency: Autonomous Decision Making
references/case-cloudflare-524-upload.md:134 · skillspector:EA2
- medium
Data Exfiltration: External Transmission
references/case-iot-router-migration-wpa3.md:28 · skillspector:E1
- medium
Privilege Escalation: Sudo/Root Execution
references/case-iot-router-migration-wpa3.md:63 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
references/case-proxy-tun-cname-override.md:133 · skillspector:PE2
- medium
Data Exfiltration: External Transmission
references/case-sse-rst-130s.md:18 · skillspector:E1
- medium
Data Exfiltration: External Transmission
references/case-sse-rst-130s.md:81 · skillspector:E1
- medium
Excessive Agency: Autonomous Decision Making
references/cognitive-traps.md:43 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
references/cognitive-traps.md:102 · skillspector:EA2
- medium
Data Exfiltration: External Transmission
references/compressed-request-comparison.md:55 · skillspector:E1
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:150 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:150 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:152 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:153 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:153 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:154 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:155 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:155 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:156 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:157 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:157 · skillspector:P9
- medium
Prompt Injection: Whitespace Padding
references/counter-review-pattern.md:158 · skillspector:P9
- medium
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by
scripts/mock-idle-upstream.py:12 · skillspector:RP1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-162 added, 4 changed High riskgot riskier
- v12026-11-03 Review findings
Files
Files
18 files, 214 KB in total. Names only; open them on GitHub.
- SKILL.md
- evals/evals.json
- references/case-cloudflare-524-upload.md
- references/case-iot-router-migration-wpa3.md
- references/case-proxy-tun-cname-override.md
- references/case-sse-rst-130s.md
- references/case-throughput-collapse-no-errors.md
- references/cognitive-traps.md
- references/compressed-request-comparison.md
- references/counter-review-pattern.md
- references/device-throughput-fieldwork.md
- references/http-response-completeness.md
- references/instrumentation-patterns.md
- references/intermittent-evidence-collection.md
- references/layered-isolation-experiment.md
- references/packet-capture-recipes.md
- scripts/layered-isolation-probe.sh
- scripts/mock-idle-upstream.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 engineering skills and plugins
feishu-doc-scraperdaymadeExtracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API, no LLM… High riskEngineeringResearch1.5k
ghostty-usedaymadeSnapshots local Codex/Claude CLI sessions across terminals and restores IDs in Ghostty after reboot (保存会话/重启前备份/恢复窗口), audits survivors,… High riskEngineeringAI & agents1.5k
git-safety-netdaymadeAudits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones,… High riskEngineeringAI & agents1.5k
github-opsdaymadeOperates GitHub via gh CLI and REST/GraphQL: PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org… High riskEngineeringDesign1.5k