Skip to content
skillsafebeta
← Report library
Purpose / Other

Marketing Psychology Skill Security Audit

What the author says it does (original text)

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to und

Independent security check

Security risks found

Files checked
2
Risks found
3
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.No risks found
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

Project marketing files can become an indirect prompt-injection path

Source references: 1
What we found

The Skill tells the agent to read a project marketing-context file and tailor its response from it, but never says to treat that content only as data or ignore commands embedded in it. A malicious or modified file could therefore inject instructions unrelated to the marketing task.

Why this matters

If the agent running the Skill also has file, terminal, or account permissions, injected text could induce disclosure of project information or unauthorized actions. The actual effect depends on the file contents and the agent's permissions.

This is a plausible indirect prompt-injection risk. The Skill instructs the agent to read project marketing files and use their contents to tailor recommendations, without saying to extract facts only or ignore commands embedded in them. If such a file is maliciously modified, its instructions could influence the agent’s response or later actions. The evidence shows an exposure path, not that exploitation occurred. Users can ask the author to treat these files as untrusted data and limit what is read.

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 applying mental models. Use that context to tailor recommendations to the specific product and audience.
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: 2
Medium risk

Pricing advice can steer purchases through defaults, decoys, and loss framing

Source references: 4
What we found

The Skill explicitly recommends preselecting the plan the seller wants customers to choose, using opt-out subscriptions, adding a clearly inferior decoy tier, and emphasizing losses from inaction. These techniques can make choice architecture—not genuine need—drive a purchase or subscription.

Why this matters

A seller applying the advice may increase uptake of costly tiers or subscriptions, while customers may pay for something unnecessary, overlook a better option, or enter a subscription without sufficiently active consent.

The source explicitly recommends preselecting the seller’s preferred plan, subscription opt-out, an inferior decoy tier, and emphasizing losses from not acting. If implemented, these designs can use inertia, contrast, and loss aversion to affect purchase or renewal decisions. Although the default advice says it should be ethical, the Skill does not require affirmative consent, an equally prominent refusal path, or genuine value in the decoy. Users can ask for opt-in defaults and clearly disclosed prices, cancellation terms, and tier differences.

SKILL.md:166In the instructionsOpen original file
### Default EffectPeople tend to accept pre-selected options. Defaults are powerful.**Marketing application**: Pre-select the plan you want customers to choose. Opt-out beats opt-in for subscriptions (ethically applied).
Show 3 other places
SKILL.md:262In the instructionsOpen original file
### Loss Aversion / Prospect TheoryLosses feel roughly twice as painful as equivalent gains feel good. People will work harder to avoid losing than to gain.**Marketing application**: Frame in terms of what they'll lose by not acting. "Don't miss out" beats "You could gain."
SKILL.md:267In the instructionsOpen original file
### Anchoring EffectThe first number people see heavily influences subsequent judgments.**Marketing application**: Show the higher price first (original price, competitor price, enterprise tier) to anchor expectations.
SKILL.md:272In the instructionsOpen original file
### Decoy EffectAdding a third, inferior option makes one of the original two look better.**Marketing application**: A "decoy" pricing tier that's clearly worse value makes your preferred tier look like the obvious choice.
Medium risk

Retention advice deliberately raises customer switching costs

Source references: 1
What we found

The Skill presents high switching costs as a retention mechanism and recommends increasing them through integrations, accumulated data, workflow customization, and team adoption. The word “ethically” is included, but there is no requirement for portability, easy export, or easy cancellation.

Why this matters

Customers could become locked in by the cost of moving their data and workflows, making it difficult to leave even when another product is more suitable or service quality declines.

The source expressly presents higher switching costs as a retention mechanism and recommends increasing them through integrations, accumulated data, customized workflows, and team adoption. Although labeled ethical, it gives no concrete safeguards for export, portability, interoperability, or easy cancellation. If implemented, customers may find it difficult to change providers because of migration time, data, and team dependencies. Users can ask for constraints such as complete data export, open formats, and a clear exit process.

SKILL.md:400In the instructionsOpen original file
### Switching CostsThe price (time, money, effort, data) of changing to a competitor. High switching costs create retention.**Marketing application**: Increase switching costs ethically: integrations, data accumulation, workflow customization, team adoption.

Inside this skill

8 instruction sections

This Skill provides marketing-psychology models and implementation advice intended to influence buying, pricing, conversion, onboarding, and retention decisions. No scripts, installation steps, or network operations are included.

View source
SKILL.md:17In the instructionsOpen original file
Mental models are thinking tools that help you make better decisions, understand customer behavior, and create more effective marketing. When helping users:1. Identify which mental models apply to their situation2. Explain the psychology behind the model3. Provide specific marketing applications4. Suggest how to implement ethically

Before giving advice, it looks for and reads a product-marketing context file in the project, then uses that content to tailor 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 applying mental models. Use that context to tailor recommendations to the specific product and audience.

The evaluations confirm that expected outputs include concrete influence techniques such as anchoring, loss aversion, social proof, scarcity, and default selection; full A/B-test design is meant to be deferred to another Skill.

View source
evals/evals.json:6In the instructionsOpen original file
      "id": 1,      "prompt": "How can I use psychology to increase conversions on our pricing page? We sell a B2B SaaS tool with three tiers ($29, $79, $199/month).",      "expected_output": "Should check for product-marketing.md first. Should apply relevant pricing psychology models: anchoring (show the highest plan first or use a decoy), charm pricing (consider $29 vs $30), Rule of 100 (percentage vs dollar discounts), Good-Better-Best framing, loss aversion (show what they miss on lower tiers). Should also apply broader persuasion models: social proof near pricing, scarcity for limited-time offers, default effect (pre-select recommended plan). Should provide specific, actionable recommendations tied to their price points.",      "assertions": [
evals/evals.json:77In the instructionsOpen original file
      "id": 6,      "prompt": "Help me run an A/B test on which psychological principle works better for our CTA — scarcity vs social proof.",      "expected_output": "Should recognize this is an A/B test setup task, not a psychology task. Should defer to or cross-reference the ab-testing skill for the experiment design. May provide psychological context on both principles to inform the hypothesis, but should make clear that ab-testing is the right skill for designing and running the experiment.",      "assertions": [        "Recognizes this as an A/B test setup task",        "References or defers to ab-testing skill",        "May provide psychological context for hypothesis",        "Does not attempt full test design using psychology patterns"      ],
Start here · InstructionsSKILL.md
marketing-psychology
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 2 more sections are available in the original file.
Files and check records2 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
  • 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

Operations mentioned in code and instructions

Read keys or account settings
SKILL.md:233In the instructionsOpen original file
### Authority BiasPeople defer to experts and authority figures. Credentials and expertise create trust.
Lines read
545
File checksum (to compare versions)
88f12f83e0d35e8df1df1787eefe7cec889bc3378c94bde12e7c5f4d6eca33b8