Back to skill

Security audit

Super Dev Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SwiftUI app generator that discloses its generated-project output and QA handoff, with no evidence of hidden, destructive, persistent, or credential-seeking behavior.

Installers should expect this skill to create generated project files under dev-output and to hand the generated code to qa-skill for review. Avoid feeding highly sensitive PRDs unless you are comfortable with that generated-code QA workflow.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly states it will 'automatically trigger qa-skill' but does not define clear user-consent, scope, or boundary conditions for invoking another skill. Unconstrained cross-skill chaining can propagate sensitive project content to additional agents or cause unintended actions beyond the user's expectation, which is especially risky in an automated development workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill says it will create a complete Xcode project in dev-output/ but does not clearly warn that it writes files to disk or define limits on what may be created or overwritten. Silent filesystem writes can surprise users, overwrite existing work, or create a staging point for unsafe generated artifacts in environments where agents have broad workspace access.

Content

No source excerpt is available for this finding.