Back to skill

Security audit

dynamic-dashboard-builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped dashboard-building guide that emphasizes user approval, configurable endpoints, rate limits, and PII safeguards rather than hidden or destructive behavior.

Before installing, be aware that this skill is intended for dashboards connected to existing data sources. Use it only with trusted endpoints, confirm polling frequency and schema changes explicitly, and avoid exposing sensitive or PII data in generated dashboards.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The frontmatter description forces Indonesian-language instructions ('Gunakan saat user ingin...') and the compliance layer continues primarily in Indonesian, but there is no indication that the user opted into that language or that the skill is region-specific. Per the policy, forcing a specific language without user opt-in is a natural-language policy issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The trigger text says the skill activates whenever the user requests something matching the description, with only 'outside the scope description' as a negative trigger. This is ambiguous because it does not clearly distinguish borderline cases or provide a narrow, exhaustive set of allowed invocations, which could lead to unintended activation.

Content

No source excerpt is available for this finding.