ClawHub
Back to skill

Security audit

Vietnam Fullstack Jobs

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Vietnam full-stack job-search workflow that uses disclosed external searches and has no hidden persistence or destructive behavior.

Install only if you expect the agent to query public Vietnam job sites using Firecrawl. Be aware that broad prompts like "job mới" may activate it and that searches or fallback scraping can use Firecrawl API quota.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are very generic, including terms like 'job mới' and 'fullstack jobs', which can easily appear in ordinary conversation and unintentionally activate the skill. In an agent environment, overly broad triggers can cause unintended browsing or external-search behavior, increasing the chance of prompt routing mistakes and unnecessary access to external services.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The repeated trigger guidance remains underspecified and does not define boundaries for when the skill should not activate. Without specificity or counterexamples, an orchestrating agent may invoke this skill for unrelated employment or technology discussions, leading to misrouting and unintended external queries.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger examples are broad and generic, including phrases like 'job mới' and 'fullstack jobs', which can match ordinary user requests and cause this skill to activate unintentionally. Because the skill then performs multiple external searches and possible scraping automatically, accidental invocation can lead to unnecessary network activity, cost, and user-surprising behavior.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Procedure

Run all search queries automatically, without asking for confirmation. Deduplicate results across all queries and sources.

**Step 1 — Search ITviec**
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to run all queries automatically without asking for confirmation, removing a user-approval checkpoint before performing multiple external actions. In context, this increases risk because the skill chains several searches and may invoke fallback scraping, which can consume resources, trigger unwanted browsing activity, and act on ambiguous requests.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The instruction "Respond in Vietnamese" imposes a fixed language requirement. Under the policy, language constraints should either be user-selectable or clearly justified as region-specific; this file does not provide an opt-in mechanism or explicit justification for overriding user language preference.

Static analysis

No suspicious patterns detected.