ClawHub
Back to skill

Security audit

Headcount Labs — Job Search & Hiring Data

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped job-search integration, with expected external queries and optional account access.

Your search terms go to Headcount Labs. Prefer the public endpoint for account-free searches. If upgrading, approve only needed read permissions and check current billing terms; authenticated capabilities extend beyond the skill's listed tools. See the publisher's [MCP documentation](https://headcountlabs.com/mcp/).

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The only supplied operation is an installation command. Although installation can support a legitimate implementation, the chunk provides no job-related implementation or evidence connecting the installed package to the declared functionality. This assessment is limited to the visible command and does not infer what the installed package does.

Content

No source excerpt is available for this finding.

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 · README.md (reported line 17)May include surrounding context.

Then register the MCP server once:

bash
openclaw mcp set headcountlabs '{"url":"https://api.headcountlabs.com/mcp/public","transport":"streamable-http"}'

Try it

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 30)May include surrounding context.

Register the public MCP server with OpenClaw:

bash
openclaw mcp set headcountlabs '{"url":"https://api.headcountlabs.com/mcp/public","transport":"streamable-http"}'
openclaw mcp list

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 100)May include surrounding context.

URL to the OAuth endpoint:

bash
openclaw mcp set headcountlabs '{"url":"https://api.headcountlabs.com/mcp","transport":"streamable-http"}'
openclaw mcp login headcountlabs

Static analysis

No suspicious patterns detected.