ClawHub
Back to skill

Security audit

Wb Usage

Security checks for vulnerabilities and agentic risk

Overview

The local usage dashboard fits its purpose, but specially crafted session titles could run web scripts when the report is opened.

Use --json until database-derived text is safely escaped in the HTML dashboard. Reports contain private session titles, so share them carefully. Explicitly request WorkBuddy usage; the figures are local estimates, not official billing records.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Tainted flow: 'src' from os.environ.get (line 36, credential/environment) → shutil.copy2 (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/usage_report.py (reported line 42)May include surrounding context.

python
tmpdir = tempfile.mkdtemp(prefix="wb-usage-")
    dst = os.path.join(tmpdir, DB_NAME)
    shutil.copy2(src, dst)
    for suffix in ("-wal", "-shm"):
        p = src + suffix
        if os.path.exists(p):

Tainted flow: 'p' from os.environ.get (line 44, credential/environment) → shutil.copy2 (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/usage_report.py (reported line 47)May include surrounding context.

python
p = src + suffix
        if os.path.exists(p):
            try:
                shutil.copy2(p, dst + suffix)
            except OSError:
                pass
    return sqlite3.connect(dst), tmpdir

The trigger “查一下我的用量” (“check my usage”) does not specify WorkBuddy or token usage.

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

This phrase could also refer to mobile data, API quotas, or another service's usage. Although the README describes WorkBuddy, the activation instruction does not require that context or exclude unrelated usage requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.