ClawHub
Back to skill

Security audit

skill-import-harvest

Security checks for vulnerabilities and agentic risk

Overview

The scanners rated this skill suspicious because its reported workflow may trigger registry searches for ordinary requests and send request-derived terms externally without privacy safeguards.

Consider installing only if registry discovery for broad requests is acceptable. Avoid using it with confidential, personal, internal, or proprietary details, and note that scanning was partial because some referenced local paths were missing.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The activation criteria extend to virtually any request for functionality or domain knowledge.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The instruction to search the registry whenever the user needs functionality or domain knowledge extends well beyond explicit skill-discovery requests, potentially diverting ordinary tasks into unsolicited external searches and third-party content processing. Installation approval and audit requirements reduce downstream risk, but do not constrain this initial activation or its network activity.

Content

No source excerpt is available for this finding.

The workflow sends request-derived search terms to an external registry without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow turns request-derived capabilities and dimensions into multiple external registry queries without requiring sensitive-data screening or query minimization. Requests involving confidential projects, internal systems, or proprietary requirements could therefore disclose sensitive details to the registry; the later installation gate does not protect these earlier transmissions.

Content

No source excerpt is available for this finding.