ClawHub
Back to skill

Security audit

Job Hunt Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a local job-search tracker that stores career data on the user’s machine and does not show evidence of hidden network access or destructive behavior.

Before installing, be comfortable with local persistent storage of job-search details, including salary, offers, notes, and rejection history. Avoid entering information you would not want stored in plaintext on this machine, and review or delete ~/.openclaw/job-hunt-tracker/ if you stop using it.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 838)May include surrounding context.

md
5. **Quick logging** — one message to log an application
6. **Celebrate wins** — interviews and offers are big deals
7. **Analyze patterns** — which sources work, where rejections happen
8. **Never judge** — rejections are normal, not failures

---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says the skill should activate for 'any job hunting task,' which is a very broad natural-language trigger. This can overlap with many ordinary career-related conversations and makes it unclear where the skill should not activate.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
87% confidence
Finding

The skill persists user data across sessions by creating and maintaining files under ~/.openclaw/job-hunt-tracker, including sensitive career information such as applications, interview history, salary targets, notes, and offers. While local-only storage reduces exfiltration risk, persistence increases exposure to privacy leakage, unintended retention, and cross-session access if the host environment or other skills can read the same files.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

First Run Setup

On first message, create data directory:

bash
mkdir -p ~/.openclaw/job-hunt-tracker

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Several activation phrases such as 'rejected,' 'follow up,' and 'weekly report' are common expressions that may appear outside the intended job-application tracking context. The section does not provide negative examples or contextual constraints to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.