Back to skill

Security audit

job-search-agent

Security checks for vulnerabilities and agentic risk

Overview

This job-search skill is purpose-aligned and mainly provides cautious job screening, ranking, tailoring guidance, and user-approved application preparation.

Before installing, be prepared for the skill to read your resume, profile constraints, and application history and to research external job postings. Keep the tracker private, review all tailored materials and sensitive answers, and only authorize actual submissions role by role.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The code’s primary purpose is a conservative screening tool for already-researched job postings. It reads a JSON input file and outputs decisions like eligible, review, reject, already_applied, or duplicate based on URL normalization, requisition identity, application history matching, posting verification timestamps, evidence-backed gates, and compensation policy checks. The module docstring explicitly says 'No fetching or applications.' That materially differs from the declared description, which emphasizes finding and evidence-ranking opportunities, tailoring truthful materials, and preparing reviewed application packets. While use of application history is consistent with the description at a high level, the core implemented behavior is job-record validation and gating, not opportunity discovery, ranking, or application-material preparation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill appears to rely on file-read and network-backed behavior, but it does not declare any explicit tool scope or permissions boundaries. In an agent environment, this can lead to over-broad execution authority, making it easier for the skill to access sensitive profile/application data or external sites without clear policy constraints or user-visible approval boundaries.

Content

No source excerpt is available for this finding.