Security audit

Openclaw cost guardian

Security checks for vulnerabilities and agentic risk

Overview

This skill is an advisory cost-review checklist for cron jobs and model usage, with no commands, file access, credential access, or persistence in the artifact.

Installers should expect this skill to influence advice about cron schedules, polling, model selection, and LLM spending. It should not need credentials, billing access, shell commands, or file changes; treat any future version requesting those capabilities as a meaningful change to review.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The manifest description includes broad trigger language such as invocation when asked about 'costs/usage,' which can match many ordinary conversations beyond cron jobs and workflow cost reviews. Over-broad auto-invocation increases the chance the skill is pulled into unrelated contexts, causing unnecessary prompt injection surface expansion, user confusion, and potentially undesired influence over responses.