ClawHub
Back to skill

Security audit

CVE Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill sends user-supplied CVE or package lookup queries to a disclosed external API and shows no hidden local execution, persistence, or privilege behavior.

Install only if you are comfortable sending CVE search terms, package names, versions, or component identifiers to the provider's external API. Avoid sending full private dependency inventories, secrets, source code, or customer data through the free-form query unless you have approved that disclosure.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 114)May include surrounding context.

md
## References

- **Kong Route:** `https://api.mkkpro.com/security/cve-scanner`
- **API Docs:** `https://api.mkkpro.com:8010/docs`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The operation is labeled only as 'Scan Cve', which does not clearly constrain what inputs are appropriate or when the skill should be invoked. In an agent setting, vague operation descriptions increase the chance of over-broad or incorrect invocation, potentially causing the system to send arbitrary user-supplied package or software data to this endpoint without sufficient intent checking or scope control.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.