Security audit

Resume Assistant Tool Free

Security checks for vulnerabilities and agentic risk

Overview

This resume assistant is mostly a text workflow, but it asks for command and file-writing authority and makes unclear privacy claims about sensitive resume data.

Review this skill before installing. It may be acceptable only if your host platform limits tool permissions, asks before file writes or shell commands, and you are comfortable sending resume content to the agent's LLM provider. Prefer a version that removes exec, narrows file access, and corrects the privacy disclosure.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:44
Finding: Excessive Command Execution and Filesystem Permissions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The auto-activation trigger matches broad common terms like resume, polishing, and scoring, causing the skill to engage in many ordinary conversations without clear user intent. In combination with write/exec permissions, broad triggering raises the chance of unintended tool use, data handling, or file-affecting behavior.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill assures users that resume data is not uploaded to any external service, yet it also states that operation depends on an LLM API supplied by the agent. That is a material privacy misrepresentation: users may expose highly sensitive personal data under false assumptions about where it is processed.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill requests exec despite its stated purpose being text analysis, scoring, and Markdown export. Unnecessary shell capability expands the attack surface substantially, because adversarial prompt content or future workflow additions could trigger command execution unrelated to resume processing.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: L071 states the core implementation supports '创建/查询/修改/删除等操作模式', which implies broad CRUD-style operations beyond the narrowly documented resume polishing, scoring, and Markdown export. This conflicts with the surrounding manifest text that repeatedly presents the free edition as a limited, single-resume assistant without broad mutable operation modes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill describes modify/save/export-style operations without clear user-facing warnings about file-affecting behavior or when content may be written somewhere. This can mislead users into granting or accepting state-changing actions without informed consent, especially in tool-enabled agent environments.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: L087 documents config_options as supporting '修改/重置/导入操作', but elsewhere the skill is described as a lightweight resume review tool with Markdown export only. That wording advertises broader stateful or ingest capabilities not aligned with the rest of the file's stated intent for a constrained free resume assistant.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: L095 says output_format supports '导出/保存/转换操作', but L060, L312, and L327 limit the free edition to Markdown export and explicitly reserve additional format conversion for PRO. This is an active contradiction between documentation sections about what output operations are available.
Content: No source excerpt is available for this finding.