Back to skill

Security audit

my-ai-build-stack

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: all three listed components were fully scanned, and the only reported issue was judged unlikely to indicate a problem in context.

The verdict is benign, not a guarantee of zero risk. The scan reports complete coverage of the three listed components; before installing, consider whether the skill’s purpose suits your needs and review its instructions yourself.

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.

md
- Judge choice: if another judge reviews the work, name the role, and say what changes, the review checklist stays the same, only who checks it changes. A builder must never judge its own work. Common choices are Muse, or a human reviewer, both marked Suggested, not confirmed, unless the owner confirms one. Default example is Muse.