ClawHub
Back to skill

Security audit

Slither Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed local Slither wrapper, but its audit script can turn failed scans into clean-looking reports.

Install and run this only in an isolated environment, preferably with a pinned Slither version. Do not rely on a clean report unless you confirm Slither actually completed successfully; failed compilation, missing tools, or malformed output may be reported as zero findings.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:24
Finding

Unpinned Third-Party Security Scanner Dependency

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
slither-audit.py:44
Finding

Slither Execution Failures Are Reported as Clean Audit Results

Content
View full analysis
1: name = parts[1].split()[0] if parts[1] else "Unknown" findings.append({"check": name, "impact": "High", "description": line[:200]}) if findings: return {"findings": findings}, None return {"findings": [], "error": "No output"}, None except FileNotFoundError: return {"findings": [], "error": "slither not installed. Run: pip install slither-analyzer"}, None except Exception as e: return {"findings": [], "error": str(e)}, None ``` The embedded error is not handled before the Markdown report is generated: ```python if report["vulnerabilities"]: for v in report["vulnerabilities"]: print(f"- **{v['type']}** ({v['severity']})") desc = v.get("description", "") if desc: print(f" {desc[:100]}") else: print("No critical vulnerabilities found.") print() print(f"## Summary") print(f"Found {len(report['slither_findings'])} issues") ``` ### Technical Analysis The return code from `subprocess.run` is never checked. If Slither exits unsuccessfully and its output contains no line matching the custom `Detector:` parser, `run_slither` returns an empty findings list with an error embedded in the result object. Its separate `err` return value remains `None`. The same fail-open behavior occurs for `FileNotFoundError` an ...[truncated 1984 chars]
Remediation
View remediation

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill instructs the user to run shell commands (pip install slither-analyzer, python3 slither-audit.py ...) and therefore has shell-execution capability, but it does not declare any permissions or allowed-tools scope in its metadata. Missing tool scoping weakens least-privilege controls and can allow an agent runtime to grant broader command execution than reviewers or policy engines expect.

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 · slither-audit.py (reported line 17)May include surrounding context.

python
def run_slither(contract_path):
    """Run slither static analysis."""
    try:
        result = subprocess.run(
            ["slither", contract_path, "--json", "-"],
            capture_output=True,
            text=True,

Static analysis

No suspicious patterns detected.