ClawHub
Back to skill

Security audit

Unified Session — One Agent, All Devices, Zero Context Loss

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps a single-user OpenClaw setup share one conversation across chat channels by changing OpenClaw session configuration.

Install this only for a personal or single-user OpenClaw agent. Do not use it for bots that multiple people can DM, because all direct-message channels will share one conversation context until you revert dmScope to per-channel-peer.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation guidance is overly broad and includes natural-language symptoms like 'seamless', 'continue conversation', or 'the AI doesn't remember', which can cause the skill to trigger during ordinary support conversations. Over-activation is risky here because the skill recommends changing session-scoping behavior in a way that can merge contexts across channels, potentially leading to privacy leakage if applied inappropriately.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
60% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 191)May include surrounding context.

md
## Security

- This skill does NOT send data anywhere
- This skill does NOT modify system files outside OpenClaw config
- This skill does NOT require API keys or credentials
- All changes are to `~/.openclaw/openclaw.json` only
- Fully reversible

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file includes a full Chinese section alongside English, but it does not explain how the skill handles language or whether users can choose their preferred locale. Because language/locale policy violations apply to natural-language instructions, this can be read as imposing a locale-specific interaction mode without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The document includes a full Chinese section and even instructs the user to say a Chinese trigger phrase, but it does not state that language selection is optional or user-driven. Under the language/locale policy, forcing or assuming a specific language without opt-in can be a violation unless clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.