ClawHub
Back to skill

Security audit

Feedback Controller

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only workflow review skill that may activate broadly, but it does not show hidden code, data access, persistence, or destructive behavior.

Install this if you want an agent to proactively diagnose execution drift and structure correction decisions. If you prefer manual control or are working on approval-sensitive tasks, consider disabling implicit invocation or calling the skill explicitly.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation triggers are phrased broadly enough that this skill could be invoked for many loosely related situations, including normal iterative tasks rather than true execution-drift scenarios. Over-broad activation increases the chance of unintended routing and can force a rigid correction protocol where it is not appropriate, which may degrade outputs or create unsafe retry/escalation behavior in higher-risk workflows.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill enables implicit invocation (`allow_implicit_invocation: true`) without any narrowly scoped trigger constraints in the file. That increases the chance the agent will invoke this controller unexpectedly and alter execution flow, which can cause unauthorized escalation, retries, or workflow interference in contexts where the user did not explicitly request it.

Static analysis

No suspicious patterns detected.