ClawHub
Back to skill

Security audit

Friendly Python

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static Python coding-guidance package with broad but disclosed triggers and no evidence of hidden execution, persistence, or data collection.

Install this if you want general Python style and design guidance. Be aware it may activate for many Python-related tasks, and treat the network/auth examples as patterns to adapt carefully rather than code to paste with real credentials.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger section says to use the skill when 'writing new code, refactoring, reviewing, or designing public APIs/CLIs' and also for 'Python or files with .py.' This is very broad and does not clearly distinguish when the skill should activate versus when it should not, increasing the chance of unintended invocation across routine Python-related work.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/reuse-composition.md (reported line 45)May include surrounding context.

python
auth = VolcAuth(service_info, credentials)
res = requests.post(url, json=body, auth=auth)

Static analysis

No suspicious patterns detected.