Back to skill

Security audit

skill-namer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: one scanner reported no findings, while the other noted a broad activation condition and flagged content for review, with some script analysis incomplete.

The verdict is benign, but not risk-free. Skillspector’s analysis was partial: it scanned 7 of 11 components, and tool-misuse analysis was incomplete for four scripts. Consider whether the broad activation condition fits your needs, and bear in mind that the available scan evidence does not fully cover those scripts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

The activation condition covers any user-described workflow, without limiting it to requests for primitive discovery or naming.

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

Describing a workflow is common in requests for debugging, documentation, or process improvement and does not necessarily indicate a desire to identify and name missing primitives. The later agent-economy examples are illustrative rather than explicit activation constraints, so they do not narrow this condition.

Content

No source excerpt is available for this finding.