Back to skill

Security audit

Cb Data Privacy Readiness Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive privacy-readiness checklist skill with no executable code or hidden system access.

This appears safe to install as a planning aid. Treat its outputs as non-legal guidance, avoid pasting unnecessary personal data or customer records, and verify jurisdiction-specific compliance steps with qualified privacy counsel before acting.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L14 states that documentation is "English-first," which is a natural-language locale constraint. The file does not indicate that users can choose another language or that the constraint is justified by a region-specific requirement, so it conflicts with the language/locale policy guidance.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

Lines L014-L015 state that the skill 'does not execute code, call APIs, access the network, scrape websites, submit forms, make purchases, send messages, or perform any external action.' However, later guidance explicitly tells users to generate cookie banners with Cookiebot and edit documents in Notion/Google Docs, which contradicts the stated no-external-action framing by operationalizing concrete third-party service usage. This is an intent/documentation contradiction rather than a mere omission.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example prompt begins with "Help me compare two markets," which is a generic conversational phrase rather than a narrowly scoped invocation. In a markdown skill description, this can make activation cues less specific and increase the chance of unintended matching with ordinary user requests.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

L132 asserts the skill remains purely descriptive with no network access or external side effects. Yet the example scenario at L146 recommends using online services such as Cookiebot, iubenda, and FreePrivacyPolicy, which conflicts with the strict framing that the skill is purely non-external in nature. The contradiction is in the documentation's claimed boundaries versus the prescribed behavior in example outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file is a markdown skill description, and these lines introduce a scenario entirely in Chinese. Under the policy rule, forcing or assuming a specific language without explicit user choice can be a locale/language policy issue, especially because the surrounding document does not explain that multilingual output is optional or user-selected.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest specifies "language": "en", which imposes a single language setting. Under the policy, locale or language restrictions should either offer user choice or be clearly justified as region-specific, and neither is present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.