ClawHub
Back to skill

Security audit

ats-job-boards-research

Security checks across malware telemetry and agentic risk

Overview

The skill is for ATS job-board research, but its helper script can also call unrelated Crawlora API endpoints with arbitrary methods and bodies, so it should be reviewed before installation.

Install only if you are comfortable giving the agent a general Crawlora API helper, not just an ATS job-board tool. Prefer reviewing or constraining scripts/crawlora.sh to the documented /jobs endpoints and read-only GET requests before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The script is advertised for ATS job-board research, but its interface accepts any API path and even documents unrelated endpoints such as Amazon, YouTube, Google search, and Google Trends. That creates a capability mismatch: any caller who can invoke the skill can repurpose it as a general Crawlora proxy, expanding data access and outbound request scope beyond the declared purpose.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The implementation forwards arbitrary GET query parameters, arbitrary HTTP methods, arbitrary JSON bodies, and arbitrary API paths to Crawlora. In the context of a narrowly scoped ATS research skill, this is dangerous because it turns the skill into a generic external API client that can be used for unintended querying, data retrieval, or policy bypass through a trusted integration.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -fsS -G "${auth[@]}" "${qs[@]}" "${base}${path}"
else
  [ -n "$body" ] || body="${rest[0]:-{}}"
  curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" -d "$body" "${base}${path}"
fi
Confidence
88% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:27