ClawHub
Back to skill

Security audit

AI intervew agent named Xiaoba

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ibaguo interview API guide, but users should treat candidate and interview data as sensitive before sending it to the external service.

Install only if you intend to use ibaguo's external interview API. Do not expose XIAOBA_API_KEY in chat or logs, obtain candidate consent where required, send only necessary candidate/resume fields, and review the provider's retention and privacy terms before using real applicant data.

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 (6)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 36)May include surrounding context.

md
-H "Accept: application/json" | jq

# POST 示例（JSON Body）
curl -sS "$BASE_URL/plans" \
  -H "Authorization: Bearer $XIAOBA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 73)May include surrounding context.

md
-H "Accept: application/json" | jq

# POST 示例（JSON Body）
curl -sS "$BASE_URL/plans" \
  -H "Authorization: Bearer $XIAOBA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 96)May include surrounding context.

  • count：题目数量（示例为 5）
bash
curl -sS "$BASE_URL/plans/generate" \
  -H "Authorization: Bearer $XIAOBA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill processes and transmits candidate personal data, resumes, interview transcripts, and evaluation results to a third-party API, but it does not clearly warn users about this external data sharing in the user-facing description or workflow guidance. This creates a privacy and consent risk because users may submit sensitive HR data without understanding that it leaves the local environment and is handled by an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This call creates candidates and may include highly sensitive personal data such as name, phone, email, plan linkage, and potentially resume_data, all of which are transmitted to an external API. In the context of an HR/interview skill, this is more dangerous than generic external transmission because it involves regulated PII and employment-related data, yet the documentation does not prominently warn users or enforce data minimization.

Content

Scanner excerpt · SKILL.md (reported line 128)May include surrounding context.

  • resume_data：简历数据（JSON 对象）
bash
curl -sS "$BASE_URL/candidates" \
  -H "Authorization: Bearer $XIAOBA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

Starting interview sessions causes interview links, scheduling information, and later interview content/results to be handled by the external service; combined with the documented result retrieval, this implies transmission and storage of sensitive candidate communications and assessments. In an employment context, this can expose transcripts, recommendations, and scoring data without sufficiently prominent disclosure, creating substantial privacy and compliance risk.

Content

Scanner excerpt · SKILL.md (reported line 154)May include surrounding context.

  • scheduled_at：计划时间（ISO 8601）
bash
curl -sS "$BASE_URL/sessions" \
  -H "Authorization: Bearer $XIAOBA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \

Static analysis

No suspicious patterns detected.