ClawHub
Back to skill

Security audit

聘才猫（Pincaimao）模拟面试

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Pincaimao mock-interview integration that sends interview and resume data to Pincaimao for the service it provides.

Install only if you are comfortable sending resume, job-description, interview-answer, and optional video data to Pincaimao. Use a dedicated API key, avoid submitting unnecessary personal information, treat cos_key and conversation_id values as sensitive, and separately review the pincaimao-basic dependency before installing it.

SkillSpector

By NVIDIA
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)

External Transmission

Medium
Category
Data Exfiltration
Content
# Step 2: 第一轮 - 开始面试
QUERY=$(echo "$JOB_INFO" | cut -c1-20)
ROUND1=$(curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
Confidence
90% confidence
Finding
This finding duplicates the same external chat transmission at line 82. The risk remains that interview data and user-provided content are sent to a third-party service, which is acceptable only with informed user consent and proper data handling controls.

External Transmission

Medium
Category
Data Exfiltration
Content
# Step 3: 后续轮次
USER_ANSWER="我有5年销售经验，擅长大客户开拓..."
curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
Confidence
90% confidence
Finding
This finding duplicates the same external chat transmission at line 104. The danger is contextual rather than hidden: continued turns may reveal increasingly sensitive information to the remote provider under a persistent conversation identifier.

External Transmission

Medium
Category
Data Exfiltration
Content
RESUME_FILE="/path/to/resume.docx"

# Step 1: 上传简历（可选）
UPLOAD=$(curl -s -X POST 'https://api.pincaimao.com/agents/v1/files/upload' \
  -H "Authorization: Bearer $PCM_MOCK_INTERVIEW_KEY" \
  -F "file=@$RESUME_FILE")
COS_KEY=$(echo "$UPLOAD" | python3 -c "import sys,json; print(json.load(sys.stdin)['cos_key'])")
Confidence
94% confidence
Finding
The upload endpoint sends a resume file to an external service and stores it in the provider's cloud object storage, which is explicitly described as sensitive. Resumes commonly contain highly sensitive personal data, so this is a true privacy and confidentiality risk even if it is core to the skill's intended behavior.

External Transmission

Medium
Category
Data Exfiltration
Content
# Step 2: 第一轮 - 开始面试
QUERY=$(echo "$JOB_INFO" | cut -c1-20)
ROUND1=$(curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
Confidence
90% confidence
Finding
This finding duplicates the same external chat transmission at line 82. The risk remains that interview data and user-provided content are sent to a third-party service, which is acceptable only with informed user consent and proper data handling controls.

External Transmission

Medium
Category
Data Exfiltration
Content
# Step 3: 后续轮次
USER_ANSWER="我有5年销售经验，擅长大客户开拓..."
curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
Confidence
90% confidence
Finding
This finding duplicates the same external chat transmission at line 104. The danger is contextual rather than hidden: continued turns may reveal increasingly sensitive information to the remote provider under a persistent conversation identifier.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.