Back to skill

Security audit

Omni-Agent Builder (OpenClaw)

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for creating OpenClaw workspaces, with one practical caution: its scaffold script can overwrite existing workspace files if run on a non-empty target.

Install only if you want an OpenClaw workspace generator. If you use the scaffold script, run it in a new empty directory or back up existing AGENTS.md, SOUL.md, USER.md, and related files first; review generated memory rules before using them with private or group contexts.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/scaffold-workspace.sh:10
Finding
Workspace Files Are Overwritten Without Confirmation or Symlink Protection<![CDATA[ ## Vulnerability Details **File Location**: `scripts/scaffold-workspace.sh`, lines 10–58 **Vulnerability Type**: Unchecked destructive file overwrite and symbolic-link following **Risk Level**: Medium ### Vulnerable Code ```bash TARGET="${1:-.}" mkdir -p "$TARGET/references" "$TARGET/memory" "$TARGET/scripts" # Minimal placeholders (you can overwrite with your customized versions) cat > "$TARGET/IDENTITY.md" <<'EOF' # IDENTITY.md - Name: Omni - Vibe: sharp, calm, practical - Emoji: 🦞 EOF cat > "$TARGET/USER.md" <<'EOF' # USER.md - Preferred name: - How to address you: - Timezone: Europe/Oslo EOF cat > "$TARGET/SOUL.md" <<'EOF' # SOUL.md You are Omni 🦞. Be direct and practical. Prefer tool-first verification when correctness matters. EOF cat > "$TARGET/TOOLS.md" <<'EOF' # TOOLS.md # Environment-specific notes (paths, aliases, services). Do not store secrets here. EOF cat > "$TARGET/AGENTS.md" <<'EOF' # AGENTS.md Every session: read SOUL.md, USER.md, memory/YYYY-MM-DD.md (today+yesterday). In main private session also read MEMORY.md if present. Safety: - Ask before destructive actions; prefer trash over rm. - Ask before outbound messages. - Stop on CLI errors; run --help and recover. - Never store credentials in this repo. EOF cat > "$TARGET/HEARTBEAT.md" <<'EOF' # HEARTBEAT.md # Keep empty to skip heartbeat. EOF cat > "$TARGET/BOOTSTRAP.md" <<'EOF' # BOOTSTRAP.md First-run ritual: 1) Ask user for mission + autonomy + boundaries + memory preference. 2) Update IDENTITY/USER/SOUL/AGENTS. 3) Seed memory/YYYY-MM-DD.md Delete this file after completion. EOF ``` ### Technical Analysis The script accepts an arbitrary destination directory and writes workspace files using truncating shell redirection. It does not determine whether destination files already exist, request confirmation, create backups, stage changes, or reject symbolic links. For regular files, `>` truncates existing content before writing the scaffold. This can destroy customized ...[truncated 1802 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Refuse to overwrite existing files by default and require an explicit `--force` or `--overwrite` option. 2. Before every write, check that the destination does not exist as a symbolic link, for example with `[[ -L "$path" ]]`. 3. When overwriting is explicitly authorized, create timestamped backups and display a diff before replacement. 4. Prefer creating the complete scaffold in a newly created staging directory, validating it, and then moving it into place. 5. Create files with no-clobber semantics where possible, such as `set -o noclobber` or an atomic exclusive-create implementation. 6. Canonicalize and validate the target directory, especially when it may be shared or controlled by another user. 7. Warn against running the script with elevated privileges and fail when the target directory or existing files have unexpected ownership. 8. Apply equivalent protections to the dated memory file written later in the script. ]]>
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The declared description emphasizes workspace generation and end-to-end construction of secure OpenClaw agents/teams, including creating multiple required files and optional memory structures. The supplied code does not create or configure anything; it only validates that certain files already exist and that AGENTS.md contains expected guardrail phrases. While validation of workspace guardrails is related to the broader domain of secure OpenClaw workspaces, the primary purpose is materially different from the declared file-generation and setup functionality. Therefore this is a description-behavior mismatch.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Session Persistence

Medium
Category
Rogue Agent
Content
- Privacy: what must never be stored?

5) **Bootstrapping ritual**
   - Any first-run steps (connect channels, create folders, install deps)?

6) **Evaluation**
   - What metrics define success?
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.

Static analysis

No suspicious patterns detected.