Skip to content
skillsafebeta
← Report library
Purpose / Other

Onboarding Skill Security Audit

What the author says it does (original text)

When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but do

Independent security check

Security risks found

Files checked
5
Risks found
5
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.Risks found: 1
Medium risk

Behavior tracking and personalized recovery can create unexpected user profiles

Source references: 5
What we found

The Skill recommends tracking activation by cohort/source, personalizing email from actions, and identifying “stalled” users from inactivity or incomplete setup for automated or human outreach.

Why this matters

Implementation can combine product behavior, acquisition source, activity status, and contact channels for profiling and recovery. Without clear notice, retention limits, or opt-out, end users may face unexpected monitoring and contact, creating privacy, compliance, and brand risk.

These are design recommendations, not code that collects or sends data by itself. If implemented, however, source, cohort, product actions, and inactivity can be used for segmentation, personalized email, and human outreach. Without notice or opt-out, this could create unexpected behavioral profiles and marketing contact. Users can ask for consent, retention limits, data minimization, opt-out controls, and clear conditions for personal outreach.

SKILL.md:88In the instructionsOpen original file
### Activation Metrics- % of signups who reach activation- Time to activation- Steps to activation- Activation by cohort/source
Show 4 other places
SKILL.md:151In the instructionsOpen original file
**Trigger-based emails:**- Welcome email (immediate)- Incomplete onboarding (24h, 72h)- Activation achieved (celebration + next step)- Feature discovery (days 3, 7, 14)**Email should:**- Reinforce in-app actions, not duplicate them- Drive back to product with specific CTA- Be personalized based on actions taken
SKILL.md:166In the instructionsOpen original file
### DetectionDefine "stalled" criteria (X days inactive, incomplete setup)### Re-engagement Tactics1. **Email sequence** - Reminder of value, address blockers, offer help2. **In-app recovery** - Welcome back, pick up where left off3. **Human touch** - For high-value accounts, personal outreach
SKILL.md:157In the instructionsOpen original file
**Email should:**- Reinforce in-app actions, not duplicate them- Drive back to product with specific CTA- Be personalized based on actions taken
SKILL.md:164In the instructionsOpen original file
## Handling Stalled Users### DetectionDefine "stalled" criteria (X days inactive, incomplete setup)### Re-engagement Tactics1. **Email sequence** - Reminder of value, address blockers, offer help2. **In-app recovery** - Welcome back, pick up where left off3. **Human touch** - For high-value accounts, personal outreach
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.Risks found: 1
Medium risk

Automatically adopting repository marketing files creates a prompt-injection path

Source references: 1
What we found

The Skill tells the agent to read and “use” several project Markdown files, without saying to treat them only as factual data, ignore embedded commands, or reconfirm sensitive actions.

Why this matters

If a repository, template, or dependency supplies a malicious marketing file, the agent's recommendations or later actions could depart from the user's request and potentially affect files, credentials, or accounts. The evidence establishes the trust path, not that exploitation occurred.

This is an active instruction to automatically read and use a repository Markdown file. If an untrusted contributor, dependency, or automation can modify that file, commands disguised as marketing context could influence later recommendations or actions. Users can ask the author to treat it strictly as untrusted data, ignore embedded operational instructions, and prevent it from authorizing file, network, or account actions.

SKILL.md:14In the instructionsOpen original file
**Check for product marketing context first:**If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 3
Medium risk

Preloaded progress can mislead end users

Source references: 2
What we found

The Skill explicitly recommends opening a checklist at 20% complete through a step performed “on their behalf,” justified by a claimed completion lift. Users may understand that number as progress they actually made.

Why this matters

If the interface does not clearly distinguish system setup from user-completed work, it creates a deceptive progress cue. It may improve short-term conversion while damaging trust and creating consumer-protection or dark-pattern risk.

What this evidence establishes

The material does recommend opening a checklist at “20% done,” but says this reflects a step completed on the user's behalf. That could represent genuine default setup or imported work, so the source does not establish that the progress is false. The risk depends on whether the interface clearly explains what was completed and by whom. Users can require progress to reflect verifiable outcomes and label system-completed steps explicitly.

This assessment concerns the code and conditions shown, not proof that harm has occurred.
SKILL.md:43In the instructionsOpen original file
The principles that make progress mechanics, checklists, and prompts actually work:- **Endowed Progress Effect** — people finish faster when progress is already started for them. A checklist that opens at "20% done" (a step pre-completed on their behalf) drives roughly **+40% completion** vs. starting at 0%. Give users a head start, don't make them start from nothing.- **Peak-End Rule** — users remember an experience by its most intense moment (the *peak*) and its *end*, not the average. Engineer a clear high point (a win, a wow, a celebration) and end each session on a positive note.
Show 1 other places
references/experiments.md:40In the instructionsOpen original file
### Progress & Motivation| Test | Hypothesis ||------|------------|| Progress bars | Show completion percentage || Checklist length | 3-5 items vs. 5-7 items || Gamification | Badges, rewards, achievements || Completion messaging | "X% complete" visibility || Starting point | Begin at 20% vs. 0% || Celebration moments | Acknowledge completions |
Medium risk

The “hook then limit” rule can encourage coercive product design

Source references: 2
What we found

The reference goes beyond comparing pricing models: it says the free experience should hook but not satisfy and that limits should make continued value require an upgrade.

Why this matters

Applied mechanically, this may intentionally weaken the free experience or introduce a pay barrier after users invest data and time, causing lock-in, refund disputes, loss of trust, or conflict with fair-design expectations for consumer products.

The reference goes beyond neutral comparison: it directs that the free experience should “hook, not satisfy” and that continued value should require payment. If used to conceal important limits, build dependency, and then impose them unexpectedly, it could impair informed purchasing decisions. Clearly disclosed feature or capacity tiers are less concerning. Users can require limits and prices to be shown before signup and prevent core work or user data from being trapped behind an upgrade.

references/activation-models.md:43In the instructionsOpen original file
## The Evernote vs. Notion parableTwo lessons on how much to give away:- **Evernote — gave away too much free.** The free tier was generous enough that most users never needed to upgrade. Free was a destination, not a doorway. Growth without matching monetization.- **Notion — hook, then limit.** Let users experience real value, then hit meaningful limits (blocks, members, features) that create a natural, well-timed reason to pay.The principle: **the free experience should hook, not satisfy.** Give enough value to prove the product and build the habit — but structure the limits so that continued value requires upgrading.
Show 1 other places
references/activation-models.md:52In the instructionsOpen original file
## Choosing1. Start from your market (Model-Market Fit), not your preference.2. Decide the card-vs-no-card tradeoff explicitly: volume of leads vs. quality of leads.3. Design the free/trial experience to hook and then limit — never to fully satisfy.4. Whatever the model, the onboarding inside it still needs the shortest possible path to value (see [minimum-path-to-value.md](minimum-path-to-value.md)).
Medium risk

Uncited precise benchmarks can mislead pricing and onboarding decisions

Source references: 3
What we found

The material gives precise effect sizes and industry benchmarks—such as a card requirement reducing signups by 50–70%, improving conversion 2–3×, and first-day abandonment rates—without a study source, sample, or applicability limits in the supplied files.

Why this matters

A team may use them to choose a card gate, trial length, or aggressive flow reduction. If its market differs from the original population, it could lose qualified users, revenue, or experimentation time.

The material presents precise effects for card requirements, trial abandonment, and prefilled progress, but the supplied text gives no study source, sample, industry, time period, or uncertainty. These figures may not transfer to a particular product yet could directly influence payment gates and onboarding design. Users can ask for verifiable sources and applicability limits, and treat the figures only as hypotheses to validate with their own data and controlled experiments.

references/activation-models.md:13In the instructionsOpen original file
### 2. Free trialFull (or near-full) access for a fixed window: **3, 7, 14, or 30 days**.- Shorter trials create urgency and force faster time-to-value; longer trials suit complex products with longer setup.- **Credit-card requirement is the key lever**: requiring a card up front **cuts signups by 50–70%**, but the users who do sign up **convert 2–3× better**. Fewer, higher-intent leads vs. more, lower-intent leads — choose based on your funnel goals.
Show 2 other places
references/minimum-path-to-value.md:13In the instructionsOpen original file
## The abandonment realityYou have far less time and patience than you think:- **40–60% of users who sign up for a free trial abandon after a single session** — and never return.- **75–80% of trial abandonment happens within the first day.**The decision to stick or bail is made almost immediately. If value isn't reached in the first session, most users are already gone. MPTV exists because the window is that small.
SKILL.md:43In the instructionsOpen original file
The principles that make progress mechanics, checklists, and prompts actually work:- **Endowed Progress Effect** — people finish faster when progress is already started for them. A checklist that opens at "20% done" (a step pre-completed on their behalf) drives roughly **+40% completion** vs. starting at 0%. Give users a head start, don't make them start from nothing.- **Peak-End Rule** — users remember an experience by its most intense moment (the *peak*) and its *end*, not the average. Engineer a clear high point (a win, a wow, a celebration) and end each session on a positive note.

Inside this skill

8 instruction sections

The Skill primarily produces onboarding audits, flows, copy, email-trigger plans, and measurement plans; the shown content contains no direct script execution or installation command.

View source
SKILL.md:200In the instructionsOpen original file
## Output Format### Onboarding AuditFor each issue: Finding → Impact → Recommendation → Priority### Onboarding Flow Design- Activation goal- Step-by-step flow- Checklist items (if applicable)- Empty state copy- Email sequence triggers- Metrics plan

It instructs the agent to read project marketing context before asking for missing information and making recommendations.

View source
SKILL.md:14In the instructionsOpen original file
**Check for product marketing context first:**If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Its method focuses on shortening the first-value path, analyzing activation and retention, and iterating onboarding through experiments.

View source
SKILL.md:27In the instructionsOpen original file
### 1. Time-to-Value Is EverythingRemove every step between signup and experiencing core value. Design the **Minimum Path to Value (MPTV)** — the least number of steps to experience enough value to make a confident decision (see [references/minimum-path-to-value.md](references/minimum-path-to-value.md)).### 2. One Goal Per SessionFocus first session on one successful outcome. Save advanced features for later.
SKILL.md:88In the instructionsOpen original file
### Activation Metrics- % of signups who reach activation- Time to activation- Steps to activation- Activation by cohort/source
Start here · InstructionsSKILL.md
onboarding
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 7 more sections are available in the original file.

File reference map

References: 4
Files making referencesReferenced content
Lines show actual file references, not execution order. Select a node to highlight its connections and inspect the files and source locations. Dashed lines include files that still need locating.
Files and check records5 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included
  • references/activation-models.mdFull text included
  • references/experiments.mdFull text included
  • references/minimum-path-to-value.mdFull text included
  • evals/evals.jsonFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions
  • evals/evals.jsonSupporting file
  • references/activation-models.mdSupporting file
  • references/experiments.mdSupporting file
  • references/minimum-path-to-value.mdSupporting file
Lines read
738
File checksum (to compare versions)
0ef9581586763aea77392f9e94a70022be2e44f6ebd0a255446feb93275a8f7d