ClawHub
Back to skill

Security audit

product-price-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed product-price research tool, but its helper script is broader than the stated purpose and can forward arbitrary requests and bodies to external API endpoints.

Review the helper script before installing. It should be treated as a general Crawlora API client, not only a product-price tool. Use it only with product-research endpoints, avoid passing sensitive data in request bodies, and do not set CRAWLORA_API_BASE unless you intentionally trust the alternate host.

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
94% confidence
Finding
The helper advertises support for unrelated endpoints such as YouTube transcripts, Google search, and Google Trends, which exceeds the stated product-price marketplace research purpose. This broadens the skill into a generic third-party data access tool, increasing the chance of misuse, policy bypass, and collection of data outside the intended scope.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The script accepts an arbitrary path, HTTP method, query parameters, and JSON body, then forwards them with the API key to the Crawlora API. In the context of a narrowly scoped product-price research skill, this creates a general API-proxy capability that can be repurposed to access unrelated endpoints and transmit arbitrary user-supplied data to an external service.

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}${path}"
fi
Confidence
90% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

External Transmission

Medium
Category
Data Exfiltration
Content
set -euo pipefail

: "${CRAWLORA_API_KEY:?Set CRAWLORA_API_KEY first — get a free key at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills}"
base="${CRAWLORA_API_BASE:-https://api.crawlora.net/api/v1}"

method="GET"
body=""
Confidence
72% confidence
Finding
https://api.crawlora.net/

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:24