ClawHub
Back to skill

Security audit

ebay-research

Security checks across malware telemetry and agentic risk

Overview

The skill is meant for eBay research, but its included helper can use the Crawlora API key to call arbitrary Crawlora endpoints beyond eBay.

Review this skill before installing. It appears useful for eBay research, but the bundled script should be treated as a general Crawlora API client, not a tightly scoped eBay tool. Use it only if you are comfortable with agents making broader Crawlora requests with your API key, or restrict the helper to the documented /ebay endpoints first.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the use of shell commands (`scripts/crawlora.sh`, `curl`, `jq`) but does not declare corresponding permissions or execution capabilities. This creates a transparency and policy-enforcement gap: an agent or reviewer may believe the skill is documentation-only or lower risk, while it actually requires command execution and outbound network access.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The skill is described as eBay-specific research, but the referenced helper (`scripts/crawlora.sh`) appears capable of making arbitrary Crawlora requests, including non-eBay endpoints and arbitrary POST bodies. That mismatch weakens least-privilege boundaries and can let a caller pivot from a narrow research skill into broader data access or unintended API actions under the same API key.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The helper is documented and implemented as a generic Crawlora client supporting unrelated endpoints such as Amazon, YouTube, and Google, even though the skill is described as eBay-only research. This creates unnecessary capability expansion: any caller able to influence the path can use the skill as a broad third-party data access proxy, increasing data exfiltration and policy-bypass risk beyond the declared scope.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The script accepts an arbitrary API path and arbitrary HTTP method/body, then forwards them directly to the Crawlora service with the stored API key. In an eBay research skill, this unjustified generic forwarding can be abused to access unrelated provider features, spend credits, transmit sensitive user-supplied data to external services, or bypass intended product restrictions.

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}${path}"
fi
Confidence
86% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

VirusTotal

64/64 vendors flagged this skill as clean.

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