ClawHub
Back to skill

Security audit

Signal CLI

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Signal messaging, but it can expose private message details in error output and should be reviewed before use.

Install only if you are comfortable letting the agent use your local Signal account to list contacts and send messages. Confirm every recipient and message before sending, and avoid using it for highly sensitive messages unless the error logging is fixed to redact message text, phone numbers, and attachment paths.

A.I.G

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/send_message.py:6
Finding

Sensitive Signal Message Data Exposed Through Failure Diagnostics

Content
View full analysis
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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes shell commands (signal-cli, python3 scripts/...) but does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap where an agent may execute local commands without a clearly constrained policy boundary, which is especially sensitive here because the commands can send real messages, enumerate contacts, and access local account data.

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/find_contact.py (reported line 5)May include surrounding context.

python
import argparse, json, re, subprocess, sys

def run(cmd):
    p = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
    if p.returncode != 0:
        raise RuntimeError(f"command failed ({p.returncode}): {' '.join(cmd)}\n{p.stderr.strip()}")
    return p.stdout

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/send_message.py (reported line 6)May include surrounding context.

python
import argparse, json, re, subprocess, sys

def run(cmd):
    p = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
    if p.returncode != 0:
        raise RuntimeError(f"command failed ({p.returncode}): {' '.join(cmd)}\n{p.stderr.strip()}")
    return p.stdout

Static analysis

No suspicious patterns detected.