Back to skill

Security audit

Payloads

Security checks for vulnerabilities and agentic risk

Overview

This is a clearly labeled dual-use security-testing payload collection with authorization warnings and no hidden execution, persistence, or credential access.

Install this only if you need security-testing payloads and will use them on systems where you have permission. Expect antivirus alerts from the EICAR file and handle the unusual filenames carefully, especially in shell commands or upload tests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This section documents offensive payloads, including an XSS-enabling SWF and phpinfo/upload-bypass references, with direct example exploit URLs and no safety, authorization, or research-only framing. In an agent skill or reusable repository context, that materially lowers the barrier to misuse by turning the README into actionable attack guidance rather than neutral defensive documentation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This section enumerates many filename variants specifically intended to bypass upload blacklists and reach executable PHP handling, including edge-case quoting and extension tricks. Providing a curated bypass set in a skill/reference file creates directly reusable attack material for unauthorized file-upload exploitation, which is more dangerous than general security discussion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.