Back to skill

Security audit

Llm Artifacts Detection

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only code-review skill for spotting AI-generated code quality issues, with no executable payload, credential use, persistence, or hidden data handling found.

This skill should be reasonable to install for code-review workflows. It may read across the codebase and, where supported, use subagents to produce review findings, so users should expect it to inspect project source files but not to make automatic edits.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (1)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/style-criteria.md (reported line 253)May include surrounding context.

items: list[str] = [] # Only hint if element type matters

text

**Redundant Hints on Clear Context**:
```python
# BAD - Context makes type obvious
user: User = User(name="Alice")