Interaction Design— agent skill

Interaction Design — independently scanned and version-tracked by SaferSkills.

by cuellarfr·Agent Skill·github.com/cuellarfr/design-skills

Is Interaction Design safe to install?

SaferSkills independently audited Interaction Design (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 23, 2026 · 31d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 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 · 4 flagged

Securityscore 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · interaction-design/SKILL.md
MEDIUMit 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
excerptinteraction-design/SKILL.md· markdown
1181. **Follow mental models** — Design based on how users *think* it works, not how it's actua
… (9 chars elided on L118)
1192. **Less is more** — Every additional element competes for attention
1203. **Provide choices, don't ask questions** — Toggles and options > confirmation dialogs
1214. **Keep tools close at hand** — Contextual toolbars, right-click menus, inline editing
1225. **Provide modeless feedback** — Status information that doesn't interrupt. Progress indic
… (32 chars elided on L122)
Occurrences
1 occurrence · at L120
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-01sha256ce5204b52388d24frubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · interaction-design/references/microinteractions.md
MEDIUMit 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
excerptinteraction-design/references/microinteractions.md· markdown
157| Onboarding walkthrough | "Tip of the day" (dismissible) | Nothing — user knows the product
… (2 chars elided on L157)
158| Default view with essential options | "Show advanced" toggle remembered | Advanced always
… (30 chars elided on L158)
159| Confirmation dialogs for destructive actions | "Don't ask again" checkbox | Skip confirmat
… (19 chars elided on L159)
160 
161### Mode Design Rules
Occurrences
1 occurrence · at L159
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-01sha25615dae9807bd892c6rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · interaction-design/references/product-behavior.md×2
MEDIUMit 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
excerptinteraction-design/references/product-behavior.md· markdown
89 
901. **Follow mental models** — Design based on how users think, not how the system is built.
… (108 chars elided on L90)
912. **Provide choices, don't ask questions** — "Bold / Italic / Underline" toggles > "How wou
… (40 chars elided on L91)
923. **Keep tools close at hand** — Contextual toolbars near selection. Right-click menus at c
… (45 chars elided on L92)
934. **Provide modeless feedback** — Status information visible in the interface, not in dialo
… (53 chars elided on L93)
Occurrences
2 occurrences · first at L91, also L139
Show all 2 locations
Line
File
L91
interaction-design/references/product-behavior.md
L139
interaction-design/references/product-behavior.md
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-01sha256ce5204b52388d24frubric 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.