ClawHub
Back to skill

Security audit

Composer Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill locally optimizes Composer IRA allocation data and writes a local JSON report, with a documentation mismatch but no evidence of hidden access, exfiltration, or unsafe persistence.

Review the output path and finance assumptions before relying on the results. The code appears to generate a local recommendation file only, but its optimizer is simplified and the manifest claims more sophistication than the code implements.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The top-level docstring says the skill outputs to `trading_bot/composer_optimized_trad_ira.json`, but the code defines `OUTPUT` as `dashboard/composer_trad_ira_optimized.json` and later writes to that path. This is an active contradiction between documentation and implementation, not just an omitted detail.

Static analysis

No suspicious patterns detected.