Security audit

Resume Assistant Tool Free

Security checks across malware telemetry and agentic risk

Overview

This resume assistant is mostly aligned with resume review, but it under-discloses privacy implications for sensitive resume data and requests broader write/exec capability than its free Markdown workflow needs.

Review this carefully before installing. Use it only if you are comfortable sharing resume content with the agent's LLM provider, or redact personal details first. Avoid granting exec unless the platform lets you disable it, and confirm before allowing the skill to write, save, modify, or delete files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The skill presents itself as a narrowly scoped resume assistant, but the documented operation model and declared tools imply broader state-changing capabilities such as write/modify/delete and conversion flows. That mismatch can mislead users and hosting agents into granting more authority than necessary, increasing the risk of unintended file changes or abuse if the skill is auto-invoked.

Intent-Code Divergence

High

Confidence: 97% confidence
Finding: The skill claims resume data is not uploaded to external services and is handled locally, yet it also states that an LLM API is required. This is a material privacy misrepresentation: users may paste highly sensitive personal data under the false assumption it never leaves the local environment, when in practice it may be sent to a remote model provider.

Context-Inappropriate Capability

Medium

Confidence: 89% confidence
Finding: Generic exec capability is excessive for a skill whose stated purpose is resume polishing, scoring, and Markdown export. Even without an explicit exploit path in the text, unnecessary command execution materially enlarges the attack surface and could enable arbitrary local actions if the agent or future prompts route untrusted content into exec flows.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The auto-activation trigger is broad enough to match common conversation about resumes, jobs, polishing, or scoring. Over-broad triggering can cause the skill to engage unexpectedly, potentially processing sensitive personal data or invoking privileged capabilities in contexts where the user did not intend to use this skill.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: The natural-language examples encourage activation through everyday phrases without defining strong trigger boundaries. In an agent ecosystem, this raises the chance of accidental invocation and unintended handling of sensitive resume data, especially when combined with write/exec permissions.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill omits a clear warning that resume content may be transmitted to an LLM during processing. Because resumes routinely contain personally identifiable and career-sensitive information, failing to disclose model transmission prevents informed consent and increases privacy and compliance risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.