Security audit

my skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for interview practice, but it can process sensitive resume and job materials through external tools and shell-based DOCX conversion without enough disclosure or scoping.

Install only if you are comfortable sharing resume, job description, image, URL, and search-derived context with the configured tools. Prefer pasting only necessary excerpts, avoid highly personal details, and be cautious with DOCX files because the skill asks the agent to use shell-based conversion.

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (4)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly directs use of an exec tool to convert DOCX files with python-docx/pandoc, which introduces unnecessary code-execution capability into a resume/JD parsing workflow. In a document-handling context, this expands the attack surface for malicious files, unsafe shell invocation, or toolchain abuse, especially because resumes and job descriptions may come from untrusted sources.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list contains broad natural-language phrases such as general interview-help requests, which can cause the skill to activate in contexts the user did not clearly intend. That can lead to accidental processing of sensitive resumes, job descriptions, or links and may unexpectedly invoke external tools or workflows.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs sending PDFs, DOCX, images, URLs, and search queries to external tools/services but does not warn users that resumes, JDs, and related content may leave the local system or be processed by third parties. Because these documents often contain highly sensitive personal and employment information, the lack of disclosure undermines informed consent and increases privacy and data-handling risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file presents all instructions, examples, and user-facing output exclusively in Chinese, including the final activation prompt. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.