Back to skill

Security audit

Operational Framework

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent workflow guide for keeping decision logs, rollback snapshots, briefings, and TODO notes in the user's workspace.

Before installing, be aware that this skill encourages keeping persistent workflow records and rollback copies. Review snapshot paths carefully, avoid copying secrets into rollbacks unless intended, and restore into a temporary location or backup first before copying over an active workspace.

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
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md
name: Operational Framework
slug: operational-framework
version: 1.0.0
description: "A disciplined, reproducible workflow for AI agents to log decisions, create rollback snapshots, and generate briefings for any change or feature implementation."
changelog: "Initial polished release – generic, community‑ready"
metadata: {"requires":{"bins":[]},"os":["linux","darwin","win32"],"configPaths":["~/.openclaw/workspace/"]}
---

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 5)May include surrounding context.

md
name: Operational Framework
slug: operational-framework
version: 1.0.0
description: "A disciplined, reproducible workflow for AI agents to log decisions, create rollback snapshots, and generate briefings for any change or feature implementation."
changelog: "Initial polished release – generic, community‐ready"
metadata: {"requires":{"bins":[]},"os":["linux","darwin","win32"],"configPaths":["~/.openclaw/workspace/"]}
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The restore instructions explicitly copy snapshot contents back into the workspace, which can overwrite existing files, but the skill does not clearly warn about this destructive behavior or require verification before restore. In an operational workflow skill, users may execute the example directly, causing accidental data loss or rollback of unrelated changes.

Content

No source excerpt is available for this finding.