ClawHub
Back to skill

Security audit

Piglet Python Craftsman

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded Python coding guidance skill with no executable install path, hidden data access, persistence, or credential handling.

Install this only if you want Python style and refactoring guidance inspired by One Python Craftsman. It may suggest using a separate friendly-python skill if already available, but this artifact does not install or invoke extra tooling by itself.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest says to 'Use $piglet to apply One Python Craftsman patterns to Python code' but does not define when this skill should or should not activate beyond a general reference to Python code. This lacks negative examples or tighter scope constraints, making invocation conditions somewhat ambiguous in a manifest file where trigger specificity matters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.