Back to skill

Security audit

cms-publishing-adapter

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported behavior appears aligned with its purpose, while noting one approval-related finding; confidence is medium and inspection was partial.

The verdict is benign, but confidence is medium and the scan was partial because a local reference was missing. Consider whether the approval-related behavior fits your workflow, and review the skill’s instructions before installing.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 207)May include surrounding context.

md
- Destination schema is unknown and cannot be inferred.
- Required fields are missing.
- Asset upload fails for required images and policy requires complete drafts.
- Existing ranked title/meta/slug would be changed without approval.
- Readback contradicts intended content.
- CMS API reports success but required content is missing.
- Draft status would be changed unintentionally.