ClawHub
Back to skill

Security audit

Locron

Security checks for vulnerabilities and agentic risk

Overview

This skill is a safety-focused guide for operating the local Locron scheduler and its dashboard, with explicit checks before mutations and careful handling of tokens and secrets.

Install this only if you want an agent to operate your local Locron scheduler. Review requests carefully before authorizing real runs, imports, service changes, dashboard changes, token display, or plaintext value export, because those can affect durable local jobs and secrets.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
Read [references/safety.md](references/safety.md) before a mutation, import/export involving values, or a diagnosis where missed runs, overlap, or termination s

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
- Inspect `dashboard status --format json` before changing its service registration. Report registration, loaded state, URL, and token-file posture without retrieving or exposing the token.
- Run foreground `dashboard` or `dashboard serve` only when the user asks to start an interactive local session. Return its exact printed loopback URL and keep the process lifecycle explicit.
- Treat `dashboard enable`, `dashboard disable`, and `dashboard enable --reset` as service mutations without dry-run. Require current authorization, inspect status first, and read status back afterward. `--reset` rotates the access token and invalidates existing dashboard sessions; never add it merely to repair or restart the service.
- Run `dashboard token` only when the user explicitly needs the secret for local authentication. Do not place the token in URLs, command logs, durable notes, or messages to third parties, and do not claim that `dashboard status` reveals it.

## Diagnose and explain