Back to skill

Security audit

Resumy

Security checks for vulnerabilities and agentic risk

Overview

This resume-building skill appears purpose-aligned, but it sends highly personal resume data to an external service without clear privacy, retention, or download-safety disclosures.

Review this before installing if you will process real candidate or employee resumes. Treat all submitted resume and cover-letter fields as potentially sent to ToolWeb's external API, and avoid using confidential or regulated personal data unless the publisher provides acceptable privacy, retention, deletion, and security terms.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill processes highly sensitive resume data including full names, email addresses, phone numbers, employment history, education, and potentially original resume text, but the description provides no privacy, retention, or handling warning. Users may upload personal data without understanding that it is being transmitted to a third-party service, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

The skill references and relies on an external API endpoint, meaning user-provided resume data is transmitted outside the local trust boundary to api.toolweb.in. In the context of resume generation and parsing, this external transmission includes sensitive PII and career-history data, making the absence of clear trust, privacy, and security disclosures materially risky.

Content

Scanner excerpt · SKILL.md (reported line 237)May include surrounding context.

md
## References

- Kong Route: https://api.toolweb.in/tools/resumy
- API Docs: https://api.toolweb.in:8166/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The /generate endpoint handles highly sensitive personal and professional data including full name, email, phone, employment history, education, and original resume text, but the spec contains no notice of privacy handling, retention, or user-consent expectations. This increases the risk of over-collection, unintended disclosure, or unsafe downstream use because integrators and users are not warned that they are submitting substantial PII.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The /parse-resume endpoint is described only as Parse Resume Endpoint and accepts an arbitrary object (additionalProperties: true), but the spec provides no narrowing context, expected invocation conditions, or exclusion criteria to clarify when this capability should be used versus ignored.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest advertises a /download/{filename} endpoint, which implies generated user documents can be retrieved, but there is no descriptive warning about what files are downloadable, whether they contain sensitive personal information, or how users should verify the requested file. For manifest/description review, that omission is a missing user warning because the behavior affects user data handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.