ClawHub
Back to skill

Security audit

LYGO Forkling

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local-only test agent that writes its own state files and prints dry-run proposal JSON, with no evidence of network use, credential access, publishing, or live chart mutation.

Install only if you want a local experimental agent loop that creates and updates files under its own state directory. Review generated state before using the dry-run proposal with any separate live-ingest or publishing tool.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Low
Confidence
85% confidence
Finding
This code creates directories and writes multiple files, including identity.json, CONSTITUTION.md, fitness.json, NEXT.md, and ledger.jsonl, but does not emit any explicit user-facing disclosure describing what will be created or modified. The --i-consent flag gates execution, but the code itself provides no prompt, print, or inline warning about the specific filesystem changes it will perform.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The tick path updates files under the fork, appends to the ledger, and may delete and recreate an existing snapshot directory via shutil.rmtree before copytree. Although consent is required, there is no prompt or explicit runtime warning telling the user that prior generation snapshots may be overwritten and local state will be mutated.

Scope Creep

Low
Category
Excessive Agency
Content
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT.

ClawHub distribution uses MIT-0. Lattice policy in references/SECURITY.md is not waived.
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.