Back to skill

Security audit

Translate UI Intent

Security checks for vulnerabilities and agentic risk

Overview

This skill provides UI design and frontend implementation guidance without hidden persistence, credential handling, or unrelated system access.

Install this if you want an agent to make UI decisions from repository evidence and visually verify frontend changes. Expect it to read relevant frontend files and run normal project verification commands when you ask for implementation; review any generated code changes as usual, especially in repositories where build or dev commands have side effects.

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
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broadly scoped to many common UI and frontend tasks, making it likely to be invoked across a wide range of requests. Over-broad activation can cause inappropriate routing and excessive authority over user workflows, which increases the chance that the skill influences tasks beyond its narrowly intended purpose.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 51)May include surrounding context.

md
- **Build delivery:** Continue through implementation and visual verification
  when the user asks to create or change the interface.

Do not ask the user to choose a mode when the request and repository make it
obvious.

## Enforce the Greenfield Ambiguity Gate

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 115)May include surrounding context.

md
- **Build delivery:** Continue through implementation and visual verification
  when the user asks to create or change the interface.

Do not ask the user to choose a mode when the request and repository make it
obvious.

## Enforce the Greenfield Ambiguity Gate

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The default prompt describes activation as turning a "rough UI idea" into a plan, but it does not define clear trigger boundaries or exclusion conditions. This broad phrasing could match ordinary conversation about UI ideas and unintentionally invoke the skill in contexts beyond the intended command-style use.

Content

No source excerpt is available for this finding.