Back to skill

Security audit

Lobster Search First

Security checks for vulnerabilities and agentic risk

Overview

This skill is a mostly coherent research workflow, but it asks agents to read user-level Claude configuration and can lead to unreviewed package installs.

Install only if you are comfortable with the agent inspecting your Claude configuration and installed skills while researching solutions. Before allowing package installs or MCP configuration, require explicit approval, review the package source and publisher, pin versions, and prefer sandboxed installs with lifecycle scripts disabled where possible.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:66
Finding

User-Level Claude Configuration and Skill Inventory Access

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:52
Finding

Unsafe Adoption of Dynamically Discovered Third-Party Dependencies

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

The skill explicitly instructs the agent to inspect ~/.claude/settings.json and ~/.claude/skills/, which are agent-local configuration and skill directories rather than project-scoped inputs. This can expose sensitive local configuration, enabled MCP servers, tokens, internal paths, or other metadata unrelated to the user task, violating least-privilege boundaries and encouraging access to non-repository files.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
0. Does this already exist in the repo? → `rg` through relevant modules/tests first
1. Is this a common problem? → Search npm/PyPI
2. Is there an MCP for this? → Check `~/.claude/settings.json` and search
3. Is there a skill for this? → Check `~/.claude/skills/`
4. Is there a GitHub implementation/template? → Run GitHub code search for maintained OSS before writing net-new code

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

md
## Anti-Patterns

- **Jumping to code**: Writing a utility without checking if one exists
- **Ignoring MCP**: Not checking if an MCP server already provides the capability
- **Over-customizing**: Wrapping a library so heavily it loses its benefits
- **Dependency bloat**: Installing a massive package for one small feature