ClawHub
Back to skill

Security audit

tesla-jobs-research

Security checks across malware telemetry and agentic risk

Overview

This Tesla jobs skill mostly does what it says, but its helper script is broader than the stated purpose and can call unrelated Crawlora API endpoints with the user's API key.

Review before installing. Use a Crawlora key you are comfortable exposing to this tool, avoid placing sensitive personal data in search fields, and prefer limiting or editing the helper so it only calls /tesla-jobs/list and /tesla-jobs/job.

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 (4)

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The helper advertises and supports unrelated Crawlora endpoints such as Amazon, YouTube, Google search, and Google Trends even though the skill is supposed to research Tesla job postings only. This scope mismatch creates an over-privileged primitive that can be repurposed by prompts or wrappers to exfiltrate data or access unintended external resources through the user's API key.

Context-Inappropriate Capability

Medium
Confidence
99% confidence
Finding
The script accepts arbitrary API paths, HTTP methods, query parameters, and POST bodies, then forwards them directly to Crawlora with the user's API key. In the context of a Tesla-jobs-only skill, this is a dangerous capability expansion because any caller that can influence arguments effectively gains a general-purpose external web/API access tool under the guise of a narrow research skill.

External Transmission

Medium
Category
Data Exfiltration
Content
- Get a free Crawlora API key (2,000 credits/mo, no card) at [https://crawlora.net](https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills).
- `export CRAWLORA_API_KEY=sk_your_key_here`
- All requests: `x-api-key: $CRAWLORA_API_KEY` against
  `https://api.crawlora.net/api/v1`. Missing/invalid key → `401`.

## How it works
Confidence
92% confidence
Finding
https://api.crawlora.net/

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}${path}"
fi
Confidence
95% confidence
Finding
curl -fsS -X "$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:21