ClawHub
Back to skill

Security audit

Campus Candidate Screener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed HR screening helper with privacy considerations around candidate contact details, but no hidden execution, persistence, or exfiltration behavior was found.

Use this only with candidate data that your organization is authorized to process. Because the default shortlist includes phone and email, consider asking the agent to redact or omit contact details until interview outreach is actually needed, and keep final hiring decisions under human review.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly requires inclusion of candidates' phone numbers and email addresses in the output shortlist, but provides no data minimization, access control, consent, or warning about handling personally identifiable information. In an HR screening workflow, this can cause unnecessary exposure of applicant PII to downstream users, logs, chat history, or broader audiences than needed for initial screening.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file content is entirely in Chinese and provides no indication that the language should be selected based on user preference or locale. In a campus recruiting skill, forcing a single language can cause misunderstandings, reduce reviewer visibility into scoring criteria, and lead to inconsistent or biased screening outcomes if users cannot accurately interpret or validate the rubric.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction states that output should default to Chinese, but the file does not provide an opt-in choice or explain that the skill is limited to a Chinese-language HR context. This is a natural-language locale policy issue because it imposes a language preference without user selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.