ClawHub
Back to skill

Security audit

smart-sourcing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Markdown-only guide for deciding when to verify claims with sources, and its behavior is disclosed and proportionate.

This appears safe to install as a sourcing guidance skill. Expect it may activate in some broad accuracy or efficiency discussions; review any separate external plugin it links to before installing that plugin too.

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
95% confidence
Finding

The manifest trigger phrases include generic words like "accuracy" and "efficiency," which commonly appear in ordinary conversation and are not specific to this skill's sourcing behavior. The file also does not provide negative examples or tighter activation constraints to distinguish when these triggers should or should not invoke the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.