ClawHub
Back to skill

Security audit

Career Coach Ai

Security checks for vulnerabilities and agentic risk

Overview

This Chinese career-coaching skill is mostly coherent, but it tells the agent to persist personal career details without clear user consent or controls.

Install only if you are comfortable with the skill retaining career context for future use. Avoid sharing unusually sensitive details unless needed, and prefer anonymizing employers, coworkers, salary details, or job-search timing until the skill provides clear consent and deletion controls.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The title and standard opening are written as mandatory Chinese interaction guidance, and the file does not offer the user any language or locale choice. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instruction to write user career details into USER.md enables persistent retention and reuse of potentially sensitive employment information without telling the user that their data may be stored or reused later. Career history, current role, anxieties, and job-search timing can be sensitive personal data, and undisclosed persistence increases privacy, consent, and over-collection risks if the storage is later exposed or accessed beyond the current session.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to Chinese-speaking users. This may conflict with language/locale policy requirements that avoid forcing a specific language without user opt-in.

Static analysis

No suspicious patterns detected.