Back to skill

Security audit

Cb Overseas Talent Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive hiring and overseas team-planning skill with no executable code, network access, credentials, persistence, or hidden side effects.

Installers should treat the output as planning support, not legal, tax, immigration, or employment advice. Provide only the business and hiring context needed for the plan, and verify jurisdiction-specific recommendations with qualified local professionals 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "Documentation is English-first" imposes a language preference in natural language. Under the policy, language constraints should either offer user opt-in/choice or be clearly justified as region-specific; this line does neither.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The phrase 'Or just describe your overseas team-building challenge' is an open-ended activation cue without clear scope boundaries or exclusion conditions. While the domain is somewhat constrained, this wording is broad enough to match many general requests about international hiring or management without specifying what does not qualify.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

A Chinese-language scenario is embedded alongside English content, but the document does not explicitly state that response language should follow user preference or input language. This can create ambiguity around language/locale behavior and may conflict with organizational language-choice expectations if the skill implicitly switches languages without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets the skill language to "en", which imposes a specific language/locale choice. Under the stated policy, this is a finding unless the skill offers user language choice or clearly documents a justified locale restriction, neither of which appears here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.