ux-research-director— agent skill

ux-research-director — independently scanned and version-tracked by SaferSkills.

by PlevanTem·Agent Skill·github.com/PlevanTem/luban-skill

Is ux-research-director safe to install?

SaferSkills independently audited ux-research-director (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
92/100
●●●●●●●●●○
Re-scan~30s
Latest scan
ScannedJun 25, 2026 · 132d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings2 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
76
26.6 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 2 flagged

Securityscore 76 · 2 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .claude/skills/ux-research-director/references/corpora-candidates.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.claude/skills/ux-research-director/references/corpora-candidates.md· markdown
11- 主要 URL: https://dscout.com/people-nerds/erika-hall-better-research-and-design / https://ww
… (106 chars elided on L11)
12- 为什么对此 sub-specialty 有信号:Hall 是 UX research 圈最 opinionated 的 critique 来源——明确批判 focus group
… (105 chars elided on L12)
13- 如何抓取:聚焦她对常见研究失败模式的命名(focus group as theater / surveys are deceptively easy / "never ask wh
… (14 chars elided on L13)
14- 大致体量:中(约 4 篇核心访谈 + 一本 200 页书)
15 
Occurrences
1 occurrence · at L13
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25614b7852251bf4666…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .claude/skills/ux-research-director/references/source-material/01-erika-hall-critique.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.claude/skills/ux-research-director/references/source-material/01-erika-hall-critique.md· markdown
11 
121. **"Aim to be proven wrong"** — "Validate the design" 的措辞预设你是对的;研究的目的是证伪而非证实。这是 Director-级
… (13 chars elided on L12)
132. **"Never ask anyone what they want"** — 用户想被喜欢胜过想说实话。研究方法选型时,behavioral evidence > stated
… (11 chars elided on L13)
143. **"Research theater"** — Focus groups 在人造场景里产出 invalid data。Hall 直接把它命名为"剧场"
154. **"Surveys are deceptively easy"** — 表面简单,实际需要大量定性 + 定量分析、远比想象更多回应数、且常被用来错误测量"satisfactio
… (58 chars elided on L15)
Occurrences
1 occurrence · at L13
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha2565084aa178cfd9d97…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.