ClawHub
Back to skill

Security audit

Openclaw Changelog Update

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because a changelog workflow was reported to include changes to product compatibility records, extending beyond release notes; the scan was partial, so the evidence is incomplete.

Review the skill's instructions before installing, especially the part about changing compatibility records. The scan did not fully resolve referenced paths, so it cannot establish that all related material was reviewed.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The changelog workflow directs changes to product compatibility records, beyond regenerating release notes.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

A task authorized to regenerate release notes also instructs the agent to remove or modify product compatibility records, expanding its scope into behavior-affecting source changes without separate approval. Premature removal could break compatibility or migrations, and the condition 'when proven safe' provides no concrete verification criteria. The requirement for fresh product qualification when non-changelog paths change mitigates release risk, but does not prevent unauthorized source edits.

Content

No source excerpt is available for this finding.