Security audit

Resume Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward resume-editing skill with no executable code, persistence, credential use, or hidden data movement.

Installers should expect this skill to activate for many resume or job-application-related prompts and to prefer an English structured resume-review format unless the user asks otherwise. It does not appear to run code, access private files, persist settings, or transmit data.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The manifest description says to activate when a user asks to improve, rewrite, review, or tailor a resume or CV, or merely mentions terms like resume/CV/求职. This is broad enough to trigger on general discussion about resumes or job applications, without clear constraints distinguishing when the skill should and should not activate.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill is framed around overseas job markets and later mandates a fixed output structure in English-language section headings, but it does not state that the user may choose the output language. Because the trigger set explicitly includes Chinese terms, this can impose a language/locale style without user opt-in.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The listed triggers include broad actions like improve, review, polish, and even simple mention of terms such as "cover letter" or "job application." Without negative examples or scope limits, the skill may activate in situations where the user is discussing application materials rather than requesting this specific resume-optimization behavior.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The file says to 'Always structure the response as' followed by English headings, which hard-codes a language and presentation style. Since the skill may be invoked by users using Chinese terms and does not offer a language choice, this is a natural-language locale policy concern.

Static analysis

No suspicious patterns detected.