Back to skill

Security audit

TaskFlow ClawHub Upload Runbook

Security checks for vulnerabilities and agentic risk

Overview

This is a small, transparent runbook for publishing a skill with the ClawHub CLI, with no hidden code or unrelated behavior.

Before installing, users should understand that following the final publish command will upload or update a skill in ClawHub using their authenticated account. Use the dry-run and inspect commands first, and only run the non-dry-run publish command for a skill folder they intend to publish.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
- A skill folder containing `SKILL.md` with valid frontmatter (`name`, `description`).