Back to skill

Security audit

AI 简历纠错排版大师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent resume review and DOCX generation tool, with manageable privacy and dependency hygiene concerns but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you are comfortable providing resume content to the skill. Use the anonymized mode before sharing output externally, watch for the fixed AI_Beautified_Resume.docx filename overwriting an existing file, and prefer a version with pinned dependencies and clearer privacy disclosure.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
requirements.txt:1
Finding

Unpinned and Unnecessary Third-Party Dependencies

Content
View full analysis
Remediation
View remediation
``` 3. Generate and enforce cryptographic hashes using a lock-file workflow such as `pip-compile --generate-hashes`. 4. Install with hash verification enabled: ```bash python -m pip install --require-hashes -r requirements.txt ``` 5. Obtain packages only from approved indexes over TLS, and prevent fallback to untrusted indexes. 6. Add automated dependency vulnerability and license scanning to the release process. 7. Review and deliberately update locked dependencies rather than resolving the latest release during deployment. ]]>

T09 · Insecure Skill Coding Practices

Note
Location
scripts/resume_beautifier_pro.py:55
Finding

Predictable Output Path Allows Silent File Overwrite

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

All user-facing natural-language content in this file is Chinese, and the README does not indicate that the language is optional or that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate a language/locale policy when a specific language is effectively forced without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The natural-language content throughout the skill file requires Chinese comprehension and does not provide users any opt-in, alternative language, or explanation that the skill is intended only for a Chinese-speaking or region-specific audience. This can violate language/locale policy when a skill effectively forces one language without user choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This code file performs a file write by generating AI_Beautified_Resume.docx from the provided resume text, which may contain sensitive personal data. Although anonymization is documented as optional, there is no visible prompt, log, or other user-facing disclosure here that a local file containing the resume will be created.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README advertises privacy masking for resumes but does not warn users that the tool must first process raw resume content that may include phone numbers, email addresses, employment history, and other personal data. This creates a privacy-transparency issue: users may assume the tool is safe for sensitive data without understanding what data is ingested, retained, or exposed during processing.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The dependency is specified without a version pin, which makes builds non-reproducible and can unexpectedly pull in a vulnerable or incompatible release. In this file, that risk is heightened because python-docx has known historical advisories and the manifest provides no assurance that a fixed version will be installed.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
python-docx
pdfplumber

Unverifiable Dependency: python-docx has 2 known advisory(ies) (CVE-2016-5851 (Improper Restriction of XML External Entity Reference in python-docx); CVE-2016-5851 (python-docx before 0.8.6 allows context-dependent attackers to conduct XML Exter)), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
90% confidence
Finding

python-docx has known XXE-related advisories in older releases, and because no version is pinned, the deployment could install an affected version. If the skill processes attacker-controlled DOCX files, XXE flaws can enable unintended file access, SSRF-style behavior, or parser abuse depending on runtime configuration.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
88% confidence
Finding

The pdfplumber dependency is also unpinned, so installations may resolve to different versions over time, including versions with future vulnerabilities or breaking changes. While no specific advisory is cited here, leaving it unpinned weakens supply-chain integrity and reproducibility.

Content

Scanner excerpt · requirements.txt (reported line 2)May include surrounding context.

text
python-docx
pdfplumber

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The comment on L09 states that the initialization 'avoids platform binary restrictions,' implying some compatibility or binary-handling behavior. In reality, L10 calls _ensure_templates(), which merely creates a templates directory and a few .docx template files, so the documentation actively mischaracterizes what the code is doing.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code automatically creates a templates directory and saves new .docx files when the class is initialized, but there is no confirmation prompt, logging, or comment directed at the user warning that filesystem changes will occur. Because this is a code file and the behavior performs file writes, it meets the missing user warning criterion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The _create_docx method saves a generated .docx file to output_path, which is a file write operation, but the code contains no confirmation prompt, user-visible log, or user-facing warning about writing output to disk. The internal docstring describes rendering behavior, but it does not serve as a disclosure to the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file contains natural-language comments, docstrings, and user-visible strings such as the error message on L13 entirely in Chinese. This can violate language/locale policy when the skill forces a specific language without user opt-in or any documented locale constraint.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The anonymize method docstring at L41 says privacy masking is used only when the user selects it, and the run_beautify docstring at L49-L52 confirms the default is False, meaning contact information remains visible unless explicitly requested. This is an intent-relevant divergence because the privacy-oriented wording can imply safer handling than the actual default behavior when producing the output file.

Content

No source excerpt is available for this finding.