ClawHub
Back to skill

Security audit

sports-scores-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a sports-data helper, but its bundled script also exposes a broad Crawlora API wrapper that can call non-sports endpoints.

Review before installing if you expect a sports-only skill. It requires a Crawlora API key and sends requests to Crawlora; normal sports endpoint use is disclosed, but the helper can also be used as a generic Crawlora API wrapper unless the publisher restricts it.

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
97% confidence
Finding
The helper advertises and supports generic Crawlora endpoints such as Amazon, YouTube, Google Search, and Google Trends, which are unrelated to the declared sports-scores-only skill scope. This creates a capability mismatch: a caller can use the bundled script as a general web research/scraping proxy, expanding data access beyond what users and reviewers would reasonably expect from the manifest.

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script forwards arbitrary paths, methods, query parameters, and JSON bodies directly to the Crawlora API, effectively exposing unrestricted API access through the skill. In the context of a sports-only skill, this is dangerous because it enables off-scope scraping/research actions, potential collection of unrelated external data, and misuse of the API key under the guise of a narrower capability.

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

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:25