Accounting Cpa Tax Marketing Kit

• Outcome: Review
• Latest audit: Sep 16, 2026 · 8:09 AM UTC
• Version: 1.0.0

Overview

The skill is a CPA marketing prompt kit, but it needs Review because it can place tax preparer identifiers such as PTINs into public marketing without enough safeguards.

Before installing or using this skill, treat PTIN, EFIN, and enrolled-agent numbers as sensitive unless you have confirmed they are required for the specific channel and jurisdiction. Prefer placeholders in drafts, remove unnecessary identifiers before publishing, and have compliance counsel or the relevant licensing board rules reviewed for ads, emails, SMS, and web copy. If installing from the README, use a pinned and trusted ClawHub installer version rather than an unversioned npx command.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

• Location: prompts/01_firm_brand_acquisition.md:8

Finding

Public Disclosure of Tax Preparer Identification Numbers

Content

View full analysis

Remediation

View remediation

T08 · Insecure Dependencies

Warning

• Location: README.md:51

Finding

Unpinned Third-Party Package Execution Through npx

Content

View full analysis

Remediation

View remediation

install accounting-cpa-tax-marketing-kit ``` 2. Document the expected package registry, publisher identity, and reviewed version. 3. Publish and verify package signatures or integrity hashes where supported. 4. Provide a trusted platform-native installation path that does not execute a mutable latest package. 5. Instruct users to inspect package provenance before execution, for example by reviewing package metadata and release signatures. 6. Avoid recommending execution from administrative or root accounts. 7. Add a lockfile or equivalent integrity metadata if the project later introduces executable dependencies. 8. Establish a release process that includes dependency review, provenance attestations, and automated supply-chain scanning. 9. Consider a two-step installation procedure that downloads a pinned artifact, verifies its checksum, and only then executes it. ]]>

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 97% confidence

Finding

The README instructs users to run npx clawhub install accounting-cpa-tax-marketing-kit without pinning a specific version of the package/tooling. npx resolves and executes the latest available package version by default, which creates a supply-chain risk: a compromised upstream package, malicious update, or typo/squat in the distribution path could lead to arbitrary code execution on the user's machine during installation.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md

**5. Facebook/Instagram Ad Creative Set (3 ads)**
Ad 1: Tax season urgency (deadline-based, not fake scarcity)
Ad 2: Referral/social proof angle (no client names without consent; use "clients like you" framing)
Ad 3: Advisory services upgrade angle ("beyond tax season")
Each ad: headline (40 chars) + primary text (125 chars) + description (30 chars) + CTA + compliance footer

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · prompts/01_firm_brand_acquisition.md (reported line 71)May include surrounding context.

md

**5. Facebook/Instagram Ad Creative Set (3 ads)**
Ad 1: Tax season urgency (deadline-based, not fake scarcity)
Ad 2: Referral/social proof angle (no client names without consent; use "clients like you" framing)
Ad 3: Advisory services upgrade angle ("beyond tax season")
Each ad: headline (40 chars) + primary text (125 chars) + description (30 chars) + CTA + compliance footer

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 77% confidence

Finding

The subject line 'ITIN filer? We can help — en español también' introduces Spanish-language messaging directly in the template rather than offering a language preference choice. While mild and customer-friendly, this can be read as locale/language targeting without explicit opt-in, which is the policy area covered by SQP-3.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 75% confidence

Finding

The input example explicitly encourages targeting 'Spanish-speaking clients,' but the prompt does not state whether outputs should remain in English, switch languages, or ask for user preference. Because language-affecting behavior is implied without an opt-in or documented choice, this may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The natural-language example list includes "bilingual Spanish/English" as a preset special-program option, but the skill does not state that language selection should be based on user preference or consent. Under the policy for this audit, forced language behavior without opt-in can be a locale/language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.