ClawHub
Back to skill

Security audit

Productboard Release

Security checks for vulnerabilities and agentic risk

Overview

This Productboard planning skill is coherent, but it can change live roadmap records without clear confirmation or scoping guidance.

Install only for users authorized to modify Productboard roadmap data. Before using create, update, owner assignment, date changes, or archiving actions, confirm the target workspace/product and exact records to change, and prefer a read-only review of current features first.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly guides use of update/create tools that can change live Productboard records, ownership, statuses, and planning dates, but it does not warn the operator that these actions are state-changing or potentially affect production roadmap data. This increases the chance of unintended modifications, especially because the workflow presents writes as routine steps without confirmation or guardrails.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.