ClawHub
Back to skill

Security audit

Bytesagain Chart Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple terminal chart generator with no evidence of hidden data access, network activity, persistence, or destructive behavior.

This appears safe to install for terminal charting. Review any local data files before passing them to the command, and expect scatter plots to work with numeric coordinate data rather than arbitrary label/value categories.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code largely matches the declared chart-generation purpose: it offers bar, line, pie, and scatter visualizations in the terminal and can parse inline or file-based data for most commands. There are no suspicious undeclared capabilities such as network access, credential collection, or unrelated system actions. However, there is a material description-to-behavior mismatch for the scatter feature. The help text and declared purpose imply scatter charts can be generated from supplied CSV/inline data, but cmd_scatter itself ignores INPUT and only consumes the CHART_DATA environment variable. In the case statement, scatter sets CHART_DATA to the raw output of parse_input; for file input containing label,value rows this may work only for numeric pairs, but the help specifically says scatter takes a , while the Python parser expects numeric x/y pairs and does not properly support the advertised 'x1:y1,x2:y2' format because parse_input converts colons to commas inconsistently. This makes the scatter behavior materially less accurate than described. Overall purpose is aligned, but the implementation does not fully and accurately deliver the declared scatter-input behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.