ClawHub
Back to skill

Security audit

Interviewly

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent mock-interview API integration, but it sends and stores sensitive interview content externally without enough privacy, retention, or report-access detail.

Review this skill before installing if you may submit real candidate answers, proprietary job descriptions, personal identifiers, or regulated employment data. Confirm ToolWeb/Interviewly's privacy policy, retention/deletion terms, and report access controls before using it with confidential material.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill processes highly sensitive personal content including job descriptions, user identifiers, interview answers, voice transcription metadata, and generated evaluation reports through an external API, but the description does not warn users that this data leaves the local environment for third-party AI evaluation and storage/report generation. This omission can cause users to unknowingly submit confidential employment, company, or personal information, increasing privacy, compliance, and consent risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The report_url shows that interview results are hosted on an external service, confirming transmission and remote availability of potentially sensitive candidate performance data. In this skill's context, interview responses and evaluation reports may contain personal, employment, or proprietary information, so external exposure without strong access controls and user warning is security-relevant.

Content

Scanner excerpt · SKILL.md (reported line 109)May include surrounding context.

{ "success": true, "overall_score": 78, "report_url": "https://api.toolweb.in/api/v1/download/sess_a1b2c3d4e5f6", "message": "Interview completed. Report generated successfully." }

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 256)May include surrounding context.

md
## References

- Kong Route: https://api.toolweb.in/tools/interviewly
- API Docs: https://api.toolweb.in:8173/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The API specification states that user interview responses are evaluated by an external AI service, but it does not clearly warn users that their submitted content may be transmitted to a third-party processor and retained for processing. Because interview answers can contain sensitive personal, employment, or proprietary information, this omission creates a meaningful privacy and informed-consent risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The API description indicates that interview session state is stored in Redis and the database, but it does not clearly communicate this storage behavior to integrators or end users. This can lead to undisclosed retention of session identifiers, user linkage, and interview metadata, increasing privacy and data-governance risk even if it is not a direct code-execution flaw.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.