ClawHub
Back to skill

Security audit

gaming-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a gaming research helper, but its bundled script can call unrelated Crawlora endpoints and send arbitrary request bodies, so users should review it before installing.

Review this skill before installing if you only want a narrowly scoped gaming lookup tool. It requires a Crawlora API key and the helper can be used for non-gaming Crawlora API calls; avoid passing private data through it and consider restricting the script to /steam and /playstation endpoints.

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
93% confidence
Finding
The helper advertises and supports generic Crawlora API usage examples such as Amazon, YouTube, and Google endpoints, which exceeds the declared gaming-research scope of the skill. In an agent setting, this creates a capability mismatch: downstream prompts or tool calls could repurpose the skill for unrelated external data access and transmission, violating least privilege and potentially policy boundaries.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The script accepts an arbitrary API path and concatenates it directly onto the Crawlora base URL, enabling access to any Crawlora endpoint rather than only game-research endpoints. In the skill context, this broadens the tool from a scoped gaming lookup utility into a general-purpose external API proxy, increasing the risk of unauthorized data access or misuse by prompt injection or tool abuse.

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

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:23