ClawHub
Back to skill

Security audit

OKR for clawbot

Security checks for vulnerabilities and agentic risk

Overview

This is a plain OKR note-taking skill that persistently maintains an OKR memory file, with no code, network access, or hidden install behavior found.

Install this if you want OpenClaw to keep a persistent OKR tracking and retrospective file. Avoid putting secrets, private credentials, or sensitive personal details into OKR updates, and clarify whether general planning or reflection comments should be saved when the intent is ambiguous.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description says it should be used whenever users mention broad topics like goal management, planning, retrospectives, scoring, or knowledge capture. This can cause the skill to activate during ordinary conversations that are not intended to modify OKR state, increasing the chance of unintended reads/writes to persistent memory. In this context, the danger is operational rather than code-execution related, but persistence to memory/okr.md makes accidental activation more consequential.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The synonym guidance maps very generic business terms such as '目标', '北极星', '季度重点', and '里程碑' into OKR intent. Because these terms commonly appear outside formal OKR workflows, the agent may incorrectly infer activation and transform or store user statements as structured objectives or KRs. The surrounding skill behavior amplifies the risk because it instructs persistent maintenance of a memory file and automatic progress updates.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The trigger example '把这次经验沉淀下来' is highly generic and can appear in many unrelated contexts, making accidental skill activation plausible. On its own this is lower severity than the broader description issues, but it still contributes to over-triggering and unintended persistence of conversation content into the OKR memory file.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.