Back to skill

Security audit

Skill Quality Evaluator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only evaluator that reads skill files and writes evaluation reports, with no hidden code or external access.

Install is reasonable for normal skill-quality reviews. Before using batch mode or memory output, confirm that storing evaluation reports is acceptable for the skills being reviewed, especially if they contain private or proprietary details.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Because this is a markdown file, vague-trigger review applies. The description and heading promise applicability to 'any skill' but do not specify concrete trigger phrases, contexts, or exclusion conditions, which can cause unintended invocation across many generic evaluation requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to save evaluation output to persistent memory without requiring user consent or warning that analyzed skill contents may be retained. In environments where skills or evaluations contain sensitive, proprietary, or user-provided data, this can create unintended data retention and later disclosure risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The batch workflow aggregates results across multiple skills and writes a summary to persistent memory without notice or consent, increasing the chance of retaining sensitive metadata or proprietary skill information at scale. Aggregation also amplifies impact because multiple inputs may be centralized into a durable artifact that could be accessed later beyond the user's expectations.

Content

No source excerpt is available for this finding.