ClawHub
Back to skill

Security audit

Encoding Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward local encoding, decoding, and hashing skill with user-directed file input and no evidence of hidden access, network activity, persistence, or exfiltration.

Use this skill for local encoding, decoding, and hashing tasks. Avoid passing real passwords, tokens, or private keys directly on the command line because shell history or process listings can expose them; use stdin or carefully controlled files when handling sensitive values.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Content
# Read from stdin or file
echo "data" | python3 scripts/encode_decode.py encode base64 --stdin
python3 scripts/encode_decode.py hash sha256 --file secret.txt
```

## Supported Formats
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

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

Missing User Warnings

Low
Confidence
85% confidence
Finding
The markdown includes examples hashing a secret string and reading from a file via stdin or --file, but it does not warn users that command-line arguments, shell history, or file contents may expose sensitive data. Because this file describes skill behavior, a brief user-facing warning would help users avoid unintentionally disclosing secrets.

Static analysis

No suspicious patterns detected.