ClawHub
Back to skill

Security audit

amazon-jobs-research

Security checks across malware telemetry and agentic risk

Overview

The skill’s Amazon Jobs purpose is mostly clear, but its bundled helper can call arbitrary Crawlora API paths and send arbitrary request bodies beyond that stated purpose.

Review this before installing. The documented Amazon Jobs use case is reasonable, but the included shell helper can be reused for unrelated Crawlora endpoints and arbitrary POST requests using your API key. Only use it if you are comfortable with that broader third-party API access, and avoid sending secrets, personal data, or unrelated prompts through the helper.

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
93% confidence
Finding
The helper advertises support for unrelated endpoints such as YouTube, Google search, and trends, which exceeds the stated Amazon.jobs-only purpose of the skill. This broadens the reachable external surface and enables misuse of the skill as a generic web/API proxy rather than a narrowly scoped job-research tool.

Context-Inappropriate Capability

High
Confidence
97% confidence
Finding
The script accepts arbitrary paths and HTTP methods and concatenates them directly onto the Crawlora API base, allowing callers to invoke any Crawlora endpoint the API key can access. In an agent setting, this violates least privilege and can turn an Amazon.jobs research skill into a general outbound data-fetching or action-capable primitive.

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
82% 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}${path}"
fi
Confidence
84% confidence
Finding
curl -fsS -X "$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:22