Back to skill

Security audit

OpenClaw Knowledge Base Retriever

Security checks for vulnerabilities and agentic risk

Overview

ClawScan gives this skill a benign verdict with medium overall confidence: the completed AIG scan reported no findings, while Skillspector flagged one low-severity language-format issue and had partial coverage.

The scanners report no high-severity issue and ClawScan rates the skill benign, but confidence is medium and Skillspector coverage is partial. Consider whether the English-only index headings are acceptable and keep in mind that the scan is not a guarantee that the skill is risk-free.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

L121 requires English index section headings regardless of the user's language choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

Although the skill says it follows the user's language, it explicitly requires index section headings to remain English "either way." This imposes a natural-language constraint on generated indexes without user opt-in or a documented technical justification.

Content

No source excerpt is available for this finding.