ClawHub
Back to skill

Security audit

Clarity Analyze

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends user-provided research questions to Clarity Protocol for remote analysis, with disclosed API-key and network requirements.

Install only if you are comfortable sending research questions, variant identifiers, focus terms, and any optional context to Clarity Protocol's remote service using your CLARITY_WRITE_API_KEY. Avoid submitting secrets, regulated health data, or proprietary research unless Clarity Protocol is approved for that data.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented behavior says this is a narrow write-oriented research-question submission skill, but the analyzed behavior indicates generic GET access to arbitrary Clarity API endpoints using an optional alternate API key and no actual implementation of the claimed submission flow. This mismatch is dangerous because reviewers and users may authorize the skill under false assumptions, enabling unintended data access, endpoint probing, or secret misuse beyond the stated purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises network use and an environment-based API key requirement but does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where a host may permit broader env or network access than users expect, reducing transparency and making review and sandboxing harder.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/api_client.py (reported line 108)May include surrounding context.

python
url = API_BASE + endpoint

    try:
        response = requests.post(
            url,
            json=data,
            headers=get_headers(write=True),

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script sends user-supplied research questions and optional context to a remote API via api_post("/analysis", data) without any user-facing disclosure at the point of submission. Because questions and context may contain sensitive biomedical, proprietary, or personal research data, this can lead to unintended external data exposure, especially in automated or scripted use where users may not realize content leaves the local environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.