Security audit

Prompt Injection Tester

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only skill for authorized LLM prompt-injection testing; the risky-looking phrases are disclosed test examples, not hidden commands.

Install this only for systems you own or have permission to test. Prefer staging or isolated test environments, get explicit approval before running resource-heavy or data-mutating tests, and remove any test prompts or poisoned documents added during RAG or tool-call testing.

SkillSpector

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

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: SKILL.md:40