ClawHub
Back to skill

Security audit

Innovation Assistant by TRIZ

Security checks across malware telemetry and agentic risk

Overview

This skill openly sends user-provided TRIZ/product-design prompts to PatSnap's Eureka RD service, which is expected for its purpose but should not be used with sensitive business or regulated information unless redacted first.

Install only if you are comfortable sending the problem description and product information you provide to PatSnap/Eureka RD. Redact confidential designs, personal data, NDA-covered information, export-controlled details, and other sensitive material before use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to execute shell commands (`bash scripts/mcp_http.sh`, `curl`, `jq`) but does not declare corresponding permissions. This creates a capability mismatch: a host may allow the skill to invoke local shell tooling and make outbound HTTP requests without explicit user-visible permission gating, increasing the risk of unexpected command execution and data exfiltration.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script sends the selected tool name and arbitrary JSON arguments to a third-party endpoint over the network, but it provides no user-facing disclosure, confirmation, or data-classification guardrails before transmission. In this skill's context, the arguments may contain proprietary product designs, engineering contradictions, manufacturing details, or cost-reduction ideas, making silent exfiltration of sensitive business data a real risk even though TLS is used.

External Transmission

Medium
Category
Data Exfiltration
Content
body_file="$(mktemp)"
trap 'rm -f "$body_file"' EXIT
set +e
http_code="$(curl -sS --max-time "$timeout" -o "$body_file" -w '%{http_code}' \
  -X POST "$ENDPOINT" \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
Confidence
97% confidence
Finding
This curl call performs external transmission of the full JSON-RPC payload to a remote service, which can include user-supplied arguments and potentially sensitive innovation, design, or manufacturing information. Within this skill, external transmission is core functionality, but it is still security-relevant because there are no built-in safeguards to prevent sending confidential or regulated data to the remote endpoint.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## External Service and Privacy Notice

This skill sends the problem description and product information provided by the user to [Eureka RD](https://eureka.patsnap.com/rd/#/agentic?type=triz&start_from=hub&utm_source=mcp_skill&utm_medium=agent&utm_campaign=triz_innovation). Do not submit trade secrets, personal information, proprietary technology protected by an NDA, or export-controlled content. Abstract or redact sensitive information first when necessary. This notice is not a mandatory consent gate: for a clearly general, non-sensitive request, disclose the external call briefly and proceed without asking the user to confirm. Ask for explicit consent only when the host policy requires it or potentially sensitive content cannot be safely redacted without changing the task.

## Before Calling the Service
Confidence
82% confidence
Finding
The skill explicitly instructs the agent to transmit user-provided problem descriptions and product information to an external service without requiring confirmation for 'clearly general' requests. That autonomous decision can misclassify sensitive engineering, proprietary, export-controlled, or personal data and send it off-platform without sufficiently explicit user consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.