YC Office Hours: two modes. Use for: brainstorm this, is this worth building. (gstack)
- Stars
- 142,230
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 31 findings, highest severity high.
- Highest severity
- high
- Findings
- 31
- 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: 31 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 (31)
high · 6
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:64 · skillspector:EA5
- high
Tool Misuse: Tool Parameter Abuse
SKILL.md:251 · skillspector:TM1
- high
Tool Misuse: Chaining Abuse
SKILL.md:446 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
sections/visual-design.md:120 · skillspector:TM2
- high
Memory Poisoning: Memory Manipulation
SKILL.md:504 · skillspector:MP3
- high
Memory Poisoning: Memory Manipulation
SKILL.md.tmpl:219 · skillspector:MP3
medium · 25
- medium
Rogue Agent: Session Persistence
SKILL.md:11 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:11 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:122 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:213 · skillspector:RA2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md:435 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
sections/visual-design.md:51 · skillspector:PE2
- medium
Rogue Agent: Session Persistence
SKILL.md:445 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:600 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md.tmpl:313 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:650 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md.tmpl:23 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md.tmpl:194 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md:5 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md:22 · skillspector:RA2
- medium
Excessive Agency: Autonomous Decision Making
sections/design-and-handoff.md:101 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
sections/design-and-handoff.md.tmpl:98 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
sections/design-and-handoff.md:295 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
sections/design-and-handoff.md.tmpl:173 · skillspector:EA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md:548 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md.tmpl:389 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md.tmpl:3 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/design-and-handoff.md.tmpl:19 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/preamble.md:22 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/second-opinion.md:56 · skillspector:RA2
- medium
Data Exfiltration: External Transmission
sections/visual-design.md:106 · skillspector:E1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v2 (2.0.0)2026-11-202 changed High risk
- v1 (2.0.0)2026-11-19 High risk
Files
Files
14 files, 206 KB in total. Names only; open them on GitHub.
- SKILL.md
- SKILL.md.tmpl
- sections/design-and-handoff.md
- sections/design-and-handoff.md.tmpl
- sections/manifest.json
- sections/phase-2a-startup-diagnostic.md
- sections/phase-2a-startup-diagnostic.md.tmpl
- sections/phase-2b-builder-brainstorm.md
- sections/phase-2b-builder-brainstorm.md.tmpl
- sections/preamble.md
- sections/second-opinion.md
- sections/second-opinion.md.tmpl
- sections/visual-design.md
- sections/visual-design.md.tmpl
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 other skills and plugins
retrogarrytanWeekly engineering retrospective. Use for: weekly retro, what did we ship. (gstack) High riskOther142k
reviewgarrytanUse when you review a diff before it lands: local changes, a branch or a PR. Use for: review my changes, look over my diff, review this… High riskOther142k
unfreezegarrytanClear the freeze boundary set by /freeze, allowing edits to all directories again. Use for: unfreeze edits, unlock all directories. (gstack) Review findingsOther142k
megacavejuliusbrusseeCaveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.… No issuesOther122k