ClawHub
Back to skill

Security audit

Taskr - Persistent Task Planning & Execution for AI Agents

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed cloud task-planning skill that needs an API key; the main caution is to treat the key and stored task notes as sensitive.

Install this only if you are comfortable with task plans and notes being stored in Taskr cloud and available to agents configured with the same project and key. Treat MCP_USER_API_KEY as a secret: do not paste it into prompts, commit it, or expose it in logs/screenshots, and rotate it if exposed. Use separate projects for separate work contexts.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The setup section instructs users to obtain and place a project ID and API key into configuration, but it does not warn that these are sensitive secrets or advise against exposing them in chat logs, screenshots, shared configs, or source-controlled files. In an agent skill context, that omission is meaningful because users may follow the instructions verbatim and accidentally disclose long-lived credentials to the model, other tools, or collaborators.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.