Security audit

Resume Tailor — JD-Matched Resume & Cover Letter

Security checks for vulnerabilities and agentic risk

Overview

This skill gives resume and cover-letter tailoring instructions and does not include code, persistence, hidden execution, or unrelated data access.

Before installing, expect to share resume and job-posting content with the agent. Redact details not needed for tailoring, such as full home address, government identifiers, birth date, or other sensitive personal information, and treat regional format advice as employer-specific guidance rather than an absolute rule.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list and description are broad enough to match generic job-help requests such as 'apply for job' or 'job application materials,' which can cause the skill to activate when the user did not explicitly ask for resume tailoring. Over-broad activation increases the chance of unnecessary collection or processing of sensitive career data and can route unrelated conversations into this skill unexpectedly.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The workflow explicitly asks users to provide resumes, uploaded files, and job descriptions, but it does not warn them that resumes often contain highly sensitive personal data such as phone numbers, addresses, email addresses, employment history, and education details. Without a privacy notice or minimization guidance, users may overshare sensitive information that is not necessary for tailoring and increase exposure risk.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The statement 'Must be in French unless applying to international company' prescribes a specific language outright. Under the policy, forcing a language without user opt-in or a clearly documented justified constraint is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The line states 'Mandarin Chinese unless applying to foreign company,' which forces a specific language choice in natural-language guidance. The policy allows locale constraints only when clearly justified or offered as an opt-in choice, which is not present here.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: The phrase 'Always translate/write in the country's primary language unless you know English is acceptable' is a broad mandatory language rule. This violates the language/locale policy because it forces a language choice rather than offering user choice or framing it as context-dependent guidance.

Static analysis

No suspicious patterns detected.