Back to skill

Security audit

Software Delivery Team — Agent Configuration Bundle

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent software delivery workflow, but users should understand it can edit files, run shell commands, use web access, and store workflow memory.

Install this only in workspaces where you are comfortable allowing an agent to edit code and run development commands. Give it clear repository scope, require confirmation for release or publish steps, and do not ask it to store credentials or unrelated private data in memory.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill grants multiple roles both file-writing and shell-execution capabilities, which can directly modify the local environment and run arbitrary commands. Even though these tools may be appropriate for a software delivery workflow, the absence of any user-facing warning, scope limits, or safety constraints increases the risk of destructive or unexpected actions if the skill is misused or prompted unsafely.

Content

No source excerpt is available for this finding.