marketing-psychology
Verdict safe, but 1 finding (1 medium), mainly prompt injection. Most recent scan 2026-02-06.
The marketing-psychology skill is primarily an educational resource providing mental models and psychological principles for marketing applications. The skill contains no executable scripts, no network operations, no data exfiltration attempts, and no command injection vulnerabilities. However, it exhibits one MEDIUM severity security concern: transitive trust abuse through automatic reading of external context files. The instruction to read `.claude/product-marketing-context.md` creates an indirect prompt injection vector where malicious content in that external file could override the skill's intended behavior. Additionally, the skill has minor documentation gaps with missing optional metadata fields (LOW severity, informational only). The core content—mental models and marketing principles—appears legitimate and educational with no signs of social engineering or deceptive intent.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
SkillSpector found no issues but could not fully inspect the package, usually because SKILL.md refers to a file that is not present, so it fails closed to CAUTION instead of SAFE. Read it as "not fully checked", not as a finding. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
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,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.
- Package
- 1 file, 21 KB
- SKILL.md
- 2945 words, 12+ sections
- Code
- None. Instructions only.
- Version
- 1.0.0
SKILL.md covers: Marketing Psychology & Mental Models · How to Use This Skill · Foundational Thinking Models · First Principles · Jobs to Be Done · Circle of Competence · Inversion · Occam's Razor · Pareto Principle (80/20 Rule) · Local vs. Global Optima · Theory of Constraints · Opportunity Cost
Findings
MEDIUM Transitive Trust Abuse via External Product Marketing Context File Prompt Injectionllm
The skill instructions direct the agent to read and trust content from `.claude/product-marketing-context.md` without validation. This file is external to the skill package and could contain malicious instructions that override the skill's intended behavior. The instruction 'Check for product marketing context first: If `.claude/product-marketing-context.md` exists, read it before applying mental models. Use that context to tailor recommendations' creates a transitive trust relationship where the skill delegates authority to untrusted external content.
SKILL.md
Check for product marketing context first:
If `.claude/product-marketing-context.md` exists, read it before applying mental models. Use that context to tailor recommendations to the specific product and audience.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 21 KB |
Package contents recorded 2026-10-22 at commit a04cb61a577a. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/coreyhaines31/marketingskills
- Raw scan result: marketing-psychology-scan.json
- Badge for your README:
- Request a re-scan