ClawHub
Back to skill

Security audit

Focus Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local focus-tracking instruction set that stores brief project state in workspace files, with no code execution or external data transfer.

Install this only if you want the agent to keep a brief local record of active work in each workspace. Do not let it record secrets, credentials, sensitive personal details, or confidential notes in FOCUS.md or FOCUS-LOG.md.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description contains broad triggers such as session start, multi-step project detection, and noticing lost context, which can cause the skill to activate in many situations without explicit user intent. Because the skill performs persistent state reads and writes, overbroad invocation increases the chance of unnecessary file access, stale-context carryover, and unintended persistence of sensitive task details.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The read/write rules instruct the agent to read FOCUS.md every session start and update it across many workflow events, but they do not define scope limits, consent boundaries, or exceptions for sensitive contexts. This can lead to automatic persistence and retrieval of user or project data across sessions, including resuming stale or inappropriate context and overwriting prior focus state when the user pivots.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.