ClawHub
Back to skill

Security audit

career-coach-ai

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent career-coaching skill, but it tells the agent to persist personal career details without explicit user consent or retention controls.

Review before installing if you do not want career or workplace details remembered across sessions. Avoid entering identifiable employer, coworker, salary, or personal crisis details unless you are comfortable with the platform’s persistence behavior, and prefer anonymized examples.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to trigger on many ordinary career-related conversations, which can cause unintended invocation and routing of user interactions into this skill without clear boundaries. In a coaching skill that handles sensitive personal and employment information, overbroad activation increases the chance of unnecessary data exposure, inappropriate persistence, and advice being given outside the user’s intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction to write key user information into USER.md introduces persistent storage of personal career context without any explicit notice, consent, retention policy, or minimization guard. Because this skill collects potentially sensitive employment details, persistence can expose private information across sessions or to other components, creating privacy and cross-context data leakage risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This file presents all user-facing instructional content in Chinese and does not indicate that the language is optional or limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The title, standard greeting, and intake questions are all written as fixed Chinese-language content, with no indication that the user may choose another language. This creates a language/locale policy concern because the skill appears to prescribe a specific language by default rather than offering an opt-in or choice.

Content

No source excerpt is available for this finding.