Back to skill

Security audit

Openclaw Secret Scanning Maintainer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report GitHub Discussion comment changes beyond its stated issue and pull request purpose, while a referenced script is missing from the scan.

Review the skill's full scope before installing: it may modify GitHub Discussion comments as well as handle issues and pull requests. The referenced script was unavailable to the scan, so its behavior remains unassessed; install only if you are comfortable with that uncertainty and the reported scope.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

Deleting and recreating content is consistent with the declared redaction and cleanup purpose. However, the supplied commands explicitly target GitHub Discussions rather than issues or pull requests, extending the skill's stated resource scope. The underlying script is not supplied, so no additional behavior can be established.

Content

No source excerpt is available for this finding.

The skill mandates English for notification and replacement comments without user opt-in.

Medium
Category
Output Handling
Confidence
100% confidence
Finding

The language rule explicitly requires all notification and replacement comments to be written in English, and line L235 reiterates this requirement for all public comments. The skill neither offers a language choice nor documents a justification for this restriction.

Content

No source excerpt is available for this finding.