ClawHub
Back to skill

Security audit

WorkBuddy Skill Visibility

Security checks for vulnerabilities and agentic risk

Overview

The skill makes disclosed WorkBuddy visibility/restoration changes and includes higher-impact options, but they are scoped, documented, and user-directed.

Before installing, confirm you want a skill that can copy/delete WorkBuddy skill directories and, if explicitly invoked, patch WorkBuddy's renderer bundle. Use list/status first, review restore --dry-run output before deletion, and avoid the bundle command unless you accept the higher risk and have verified the target paths.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
python scripts/skill_visibility.py <命令> [开关]

Lp1

High
Category
MCP Least Privilege
Confidence
78% confidence
Finding

The script reads environment variables (WORKBUDDY_APP_ROOT, WORKBUDDY_CONFIG_DIR, LOCALAPPDATA, ProgramFiles, ProgramFiles(x86)) to influence filesystem targeting, but the capability is not declared by the skill metadata. In a security-sensitive agent environment, undeclared environment access reduces transparency and can let execution context unexpectedly steer which installation or config paths are modified, especially because this script can delete directories and patch application assets.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file embeds its primary natural-language documentation and user-visible CLI messages in Chinese, which effectively forces a specific language on users. The file does not offer any language selection, fallback, or justification that the skill is intended only for a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/skill_visibility.py (reported line 947)May include surrounding context.

python
try:
        with open(tmp, "wb") as handle:
            handle.write(text.encode("utf-8"))
        proc = subprocess.run([node, "--check", tmp], capture_output=True, text=True, timeout=300)
        if proc.returncode != 0:
            detail = (proc.stderr or proc.stdout or "").strip()
            if detail:

Static analysis

No suspicious patterns detected.