ClawHub
Back to skill

Security audit

Wc Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local word-count skill whose documentation overstates some features, but it does not show hidden or harmful behavior.

Install only if you need a basic line, word, and character counter for stdin or a single file; do not rely on the advertised byte counts, multi-file totals, JSON output, or longest-line option unless the skill is updated.

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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code generally matches the broad idea of a word-count utility, but it materially under-implements the declared functionality. The description promises line, word, character, and byte counts for one or more files with per-file and total summaries. The code only accepts a single optional file argument, otherwise reads stdin, and reports lines, words, and characters. There is no byte-count option or implementation, no handling of multiple files, and no total summary output. No suspicious undeclared behavior is present, but the declared description is not accurate for the actual capabilities provided.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest describes counting lines, words, characters, and bytes in one or more files with per-file and total summary. The code defines only one optional file argument, supports lines/words/chars but not bytes, and has no logic for iterating over multiple files or producing totals.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.