Security audit

Resume Tailor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed resume and interview preparation helper, with no evidence of hidden data access, credential use, persistence, or destructive behavior.

Install only if you are comfortable giving the agent your resume and job materials. Review every rewritten claim, metric, title, and ownership statement before using it, and consider pinning python-docx in a controlled environment if you run the included DOCX generator.

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 78% confidence
Finding: The skill explicitly instructs the agent to read user-provided resume files (PDF/Word/text), which is a file-read capability, but no permissions are declared. Undeclared file access weakens transparency and permission scoping, making it harder for users or the platform to understand what data the skill can access, especially since resumes often contain sensitive personal information.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: The trigger description is very broad and overlaps with ordinary job-seeking requests, increasing the chance the skill activates in contexts where the user did not intend full resume analysis and rewriting. Because the skill processes resumes and generates persuasive interview content, over-broad triggering can lead to unnecessary handling of sensitive personal data and unintentional persuasive coaching.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The example user phrases are generic and lack clear boundaries, so the skill may intercept many normal employment-related conversations. In this context, that matters because the skill handles sensitive resume content and can steer users into resume reframing and interview scripting without strong activation safeguards.

Ssd 4

Medium

Confidence: 90% confidence
Finding: The skill encourages 'ability migration translation' and reframing unrelated or weaker experiences into job-aligned narratives in ways that may mislead employers, even while stating not to fabricate facts. This creates a deception risk by helping users present experiences in a more role-relevant but potentially materially misleading way, which can undermine hiring integrity.

Ssd 4

Medium

Confidence: 93% confidence
Finding: The interview-prep section goes beyond resume polishing and prepares users for defending or sustaining 'translated' claims under questioning, including packaged course projects, quantified results, and cross-domain narratives. That materially increases the risk of facilitating deceptive representations during hiring by generating cover-story-like responses for potentially inflated or misleading resume content.

Unpinned Dependencies

Low

Category: Supply Chain
Content: python-docx>=1.1.0
Confidence: 93% confidence
Finding: The dependency is specified with a lower bound only (python-docx>=1.1.0), which allows future unreviewed versions to be installed. This can introduce supply-chain risk, unexpected breaking changes, or newly introduced malicious/compromised releases into the skill's environment without explicit approval.

Static analysis

No suspicious patterns detected.