Back to skill

Security audit

Lobster Santa Method

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed quality-review workflow that asks agents to independently review important outputs, with no executable code, hidden installation behavior, or persistent access.

Before installing, consider that using this skill can send the original task and generated output to multiple review agents and may increase token cost. It appears appropriate for high-stakes review workflows when those agents are trusted with the content being reviewed.

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 · SKILL.md (reported line 235)May include surrounding context.

md
1. Generate output
2. New context: "You are Reviewer 1. Evaluate ONLY against this rubric. Find problems."
3. Record findings verbatim
4. Clear context completely
5. New context: "You are Reviewer 2. Evaluate ONLY against this rubric. Find problems."
6. Compare both reviews, fix, repeat